© 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. 23-TRANSCODER-HP
    7. 162366
    Prev
    Next
    INDEX
    Explanations

    REST

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owi
    -0.25
    adol
    -0.24
    gings
    -0.23
    辫
    -0.23
     conce
    -0.23
    caf
    -0.23
     perfection
    -0.22
    catid
    -0.22
    icas
    -0.22
    omi
    -0.22
    POSITIVE LOGITS
    -Free
    0.26
    —one
    0.25
    æĢĿ
    0.25
    çŃı
    0.25
     Affairs
    0.25
    EMA
    0.24
    -One
    0.24
    NO
    0.23
    -Language
    0.23
    -Fi
    0.23
    Activations Density 0.026%

    No Known Activations