© 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. 108215
    Prev
    Next
    INDEX
    Explanations

    -born

    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
    轩
    -0.29
    主ä½ĵ
    -0.26
    è½»æĿ¾
    -0.25
    æİĮæı¡
    -0.24
     racing
    -0.24
    moth
    -0.24
    lichkeit
    -0.24
    nable
    -0.24
    adera
    -0.24
    ä¸ĢåIJ¬
    -0.23
    POSITIVE LOGITS
    åħ¨çIJĥ
    0.25
     "@/
    0.24
    osos
    0.24
    åĪĨè£Ĥ
    0.24
    å¤ı天
    0.24
    REP
    0.23
    asses
    0.23
    ename
    0.23
    mercial
    0.23
    .Rule
    0.23
    Activations Density 7.553%

    No Known Activations