© 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. 141379
    Prev
    Next
    INDEX
    Explanations

    Negation

    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
    宽
    -0.27
     councils
    -0.26
    æģ¯
    -0.26
    ละ
    -0.26
    _PAD
    -0.26
    tam
    -0.26
    æ³Ħ
    -0.26
    æ¯ıèĤ¡
    -0.25
    spiel
    -0.25
    龸çİĭ
    -0.25
    POSITIVE LOGITS
     MST
    0.26
     tears
    0.26
    .annotations
    0.25
     MIPS
    0.24
    AsString
    0.24
    eways
    0.24
    ä¸įä»ħè¦ģ
    0.24
    avors
    0.24
    htags
    0.23
    a
    0.23
    Activations Density 30.291%

    No Known Activations