© 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. 149887
    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
    orce
    -0.28
    ç°ĩ
    -0.25
     integrating
    -0.25
    uman
    -0.25
     integral
    -0.25
    owns
    -0.25
     rowIndex
    -0.25
    æķ´çIJĨ
    -0.24
    ¤
    -0.24
    getRow
    -0.24
    POSITIVE LOGITS
    _FF
    0.29
    ngo
    0.27
    Official
    0.26
     blat
    0.26
    æĮīæŶ
    0.25
     Furn
    0.24
     полно
    0.23
     Fabric
    0.23
    proj
    0.23
    /sites
    0.23
    Activations Density 0.076%

    No Known Activations

    This feature has no known activations.