© 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. 27-TRANSCODER-HP
    7. 8735
    Prev
    Next
    INDEX
    Explanations

    Possibly non-English terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿ¡
    -0.32
     schl
    -0.30
    utta
    -0.30
    ç»Ĩèĥŀ
    -0.28
    è¿°
    -0.28
    ptic
    -0.27
    usion
    -0.26
    足
    -0.26
    arella
    -0.26
    WER
    -0.26
    POSITIVE LOGITS
    çĽ¸äº²
    0.32
    交æµģåIJĪä½ľ
    0.29
    æľ¬æĬ¥è®°èĢħ
    0.27
    ç¿©
    0.27
     exchanged
    0.27
    åį¡è½¦
    0.26
     Ñģов
    0.26
    尾巴
    0.25
    pec
    0.25
     responsible
    0.25
    Activations Density 0.004%

    No Known Activations