© 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. 58039
    Prev
    Next
    INDEX
    Explanations

    heraldry and identification

    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
    spo
    -0.29
    çļĦ身份
    -0.26
    è¬Ģ
    -0.25
    ä¹ĭå¿ĥ
    -0.25
    sWith
    -0.25
    uncate
    -0.25
     noses
    -0.24
     clocks
    -0.24
    àªĨ
    -0.24
    -bed
    -0.23
    POSITIVE LOGITS
    URN
    0.27
     arbit
    0.27
    wort
    0.27
    mith
    0.27
    len
    0.26
    _TYPED
    0.26
    ród
    0.25
    ç»ĥ
    0.25
    åħ·ä½ĵæĥħåĨµ
    0.25
     fertil
    0.24
    Activations Density 0.003%

    No Known Activations