© 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. 30-TRANSCODER-HP
    7. 96311
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avis
    -0.29
    ecz
    -0.25
    sons
    -0.25
    çµIJ
    -0.24
    รà¸Ńà¸ĩ
    -0.24
     Merrill
    -0.24
    èĩªè±ª
    -0.24
    defense
    -0.23
    éŀĭåŃIJ
    -0.23
     trav
    -0.23
    POSITIVE LOGITS
    orean
    0.32
    CID
    0.30
    cia
    0.28
     getInstance
    0.26
    brew
    0.26
    ãĥªãĤ¢
    0.26
    ToOne
    0.26
    åĤ¬
    0.25
    .getInstance
    0.25
    åħĭåĪ¶
    0.25
    Activations Density 0.392%

    No Known Activations

    This feature has no known activations.