© 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. 149843
    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
    åħ´
    -0.30
    èĪĪ
    -0.29
    estyle
    -0.28
     tour
    -0.27
    说èĩªå·±
    -0.27
    style
    -0.27
     Exc
    -0.26
    éģĵ
    -0.26
     parenthesis
    -0.26
     Cam
    -0.25
    POSITIVE LOGITS
    è´£ç¼ĸ
    0.32
    两端
    0.29
    æīĵèµ¢
    0.29
    AreaView
    0.27
    :invoke
    0.26
    åľ¨æ¸¸æĪıä¸Ń
    0.26
    ,ep
    0.25
    FFFFFFFF
    0.25
    å¼Ģåĩº
    0.24
    械
    0.24
    Activations Density 0.079%

    No Known Activations

    This feature has no known activations.