© 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. 31-TRANSCODER-HP
    7. 19745
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    Negative Logits
    //===
    -0.28
    object
    -0.28
    getObject
    -0.28
    _Obj
    -0.27
    afx
    -0.27
     SF
    -0.27
     getObject
    -0.27
    ä¼Ļä¼´åħ³ç³»
    -0.26
    Regs
    -0.26
    $obj
    -0.26
    POSITIVE LOGITS
    str
    0.29
    Str
    0.28
     Str
    0.28
    rist
    0.26
    -str
    0.25
    lotte
    0.25
    terra
    0.25
    odu
    0.25
    æijĦ
    0.24
    TAB
    0.24
    Activations Density 14.595%

    No Known Activations