© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149446
    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
    çºł
    -0.30
    _u
    -0.26
    éĩĿ
    -0.25
    mage
    -0.24
    erts
    -0.24
    ends
    -0.24
    ificación
    -0.24
    æĹ¥åľ¨
    -0.24
     COLL
    -0.24
    åħ³åı£
    -0.23
    POSITIVE LOGITS
    ä¹Łä¸įæķ¢
    0.27
    èĥ½çľĭåĩº
    0.26
     envelop
    0.25
    éĽı
    0.24
    bear
    0.23
    ä½łèĥ½
    0.23
    Reader
    0.23
    è¯ī
    0.23
    è¾ħ
    0.23
    Primitive
    0.23
    Activations Density 0.274%

    No Known Activations

    This feature has no known activations.