© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5711
    Prev
    Next
    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĨ©
    -0.29
    ĥģ
    -0.29
    yte
    -0.29
    >tag
    -0.28
     pursuit
    -0.27
    eko
    -0.26
    ULE
    -0.26
     Nich
    -0.25
    nestjs
    -0.24
    odia
    -0.24
    POSITIVE LOGITS
    Subset
    0.27
    punk
    0.25
    iry
    0.25
    rates
    0.24
    ights
    0.24
     OUTER
    0.24
     pear
    0.23
     Sauce
    0.23
    ãģ¨ãĤĤ
    0.23
    Linked
    0.23
    Activations Density 0.013%

    No Known Activations