© 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. 149493
    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
    whelming
    -0.28
    æŁľ
    -0.27
    plate
    -0.26
     <|
    -0.26
    uant
    -0.26
    åIJİåı°
    -0.25
     plate
    -0.25
    çģ«åĬĽ
    -0.25
    殿
    -0.24
    éķ¿å¾Ĺ
    -0.24
    POSITIVE LOGITS
     change
    0.25
    æĭħ
    0.24
     descriptors
    0.24
    itles
    0.23
     changes
    0.23
    _Desc
    0.23
    eci
    0.23
    åħ¬ç½ijå®īå¤ĩ
    0.23
    ascar
    0.23
    oras
    0.23
    Activations Density 1.078%

    No Known Activations

    This feature has no known activations.