© 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. 20-TRANSCODER-HP
    7. 140959
    Prev
    Next
    INDEX
    Explanations

    Cities and places

    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
    Not in Any Lists

    No Comments

    Negative Logits
    å¼¯æĽ²
    -0.26
    á»ĩt
    -0.26
    æŃ£ä¹ī
    -0.25
    uyen
    -0.24
    vrier
    -0.24
    ä¸ĬéŨ
    -0.24
    çĵ¢
    -0.23
    Edition
    -0.23
    çİĩè¾¾åĪ°
    -0.23
     ÄijÆ°Æ¡ng
    -0.23
    POSITIVE LOGITS
    WSC
    0.29
    WB
    0.27
     ['$
    0.27
    club
    0.25
    认
    0.25
    forces
    0.24
    ofs
    0.24
    _conditions
    0.24
    <(),
    0.23
    oft
    0.23
    Activations Density 43.504%

    No Known Activations