© 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. 163380
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è·¨åĽ½
    -0.26
    urable
    -0.26
    compan
    -0.25
    tap
    -0.24
    <Address
    -0.24
    ãĥĦãĤ¢ãĥ¼
    -0.24
     discipline
    -0.24
    使çĶ¨å¯¿åij½
    -0.24
    åľ°åĿĢ
    -0.24
    ajo
    -0.23
    POSITIVE LOGITS
     earnest
    0.27
    æĨĭ
    0.26
     suff
    0.26
     Âł Âł Âł Âł
    0.25
     nomin
    0.25
     drawn
    0.25
    essional
    0.25
    ey
    0.24
    coin
    0.24
    omin
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.