© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149694
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     **************************************************************************
    -0.31
    drs
    -0.28
    (bot
    -0.26
    dr
    -0.26
    è¹Ħ
    -0.25
    dÃŃ
    -0.24
    Marcus
    -0.24
     mơ
    -0.23
    ä½ľæĸĩ
    -0.23
    ****************************************************************************
    -0.23
    POSITIVE LOGITS
    ниÑĨ
    0.27
    æĸ°æĺ¥
    0.26
    oom
    0.26
     whether
    0.25
    å°±å¾Ĺ
    0.24
    WebHost
    0.24
     cover
    0.24
     condem
    0.24
    niest
    0.24
    whether
    0.24
    Activations Density 3.639%

    No Known Activations

    This feature has no known activations.