© 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. 31-TRANSCODER-HP
    7. 18873
    Prev
    Next
    INDEX
    Explanations

    code and technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rud
    -0.32
     Bender
    -0.27
    itudes
    -0.26
    endi
    -0.26
    åħĥ
    -0.25
    Interop
    -0.25
     Jest
    -0.25
    surf
    -0.25
     surf
    -0.24
    gateway
    -0.24
    POSITIVE LOGITS
    éĵIJ
    0.28
    åħ¬åı¸ç«łç¨ĭ
    0.27
    hq
    0.24
    ëĭ¥
    0.24
    éŃĶåħ½
    0.24
    åħļçļĦ建设
    0.24
    çĨĦ
    0.23
     contractual
    0.23
    Implicit
    0.23
    åħļé£İ
    0.23
    Activations Density 3.437%

    No Known Activations