© 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. 20-TRANSCODER-HP
    7. 64656
    Prev
    Next
    INDEX
    Explanations

    Technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Fifty
    -0.26
    amt
    -0.26
    æľĭ
    -0.25
    ç¾İ好çļĦ
    -0.25
    èµĦ
    -0.25
    éĢı
    -0.24
    Past
    -0.24
     Metallic
    -0.23
    Prim
    -0.23
     Ashton
    -0.23
    POSITIVE LOGITS
    BEL
    0.27
    _TR
    0.26
    rus
    0.25
     osc
    0.24
     detached
    0.24
    åıijè¨Ģ
    0.24
    _INLINE
    0.24
    ä¸ĵ项
    0.23
     hardcoded
    0.23
    _blend
    0.23
    Activations Density 0.775%

    No Known Activations