© 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. 5823
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    Sharper
    -0.28
    gression
    -0.28
    大巴
    -0.28
    <Document
    -0.24
    mercial
    -0.24
     transmissions
    -0.24
    reeze
    -0.24
     testim
    -0.24
    raison
    -0.24
    èĥ½çľĭåĩº
    -0.24
    POSITIVE LOGITS
    ato
    0.26
     Ao
    0.26
     actual
    0.26
    濯
    0.25
    çĦ¶åIJİ
    0.25
    å®ŀè´¨
    0.25
    åľ¨æĹ¥æľ¬
    0.25
    anges
    0.24
     pop
    0.24
    ue
    0.23
    Activations Density 0.195%

    No Known Activations