© 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. 163169
    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
    弧
    -0.25
    brit
    -0.25
    æ¯ı次éĥ½
    -0.25
    ÑĢаж
    -0.24
     TSR
    -0.23
    beb
    -0.23
    éĻį临
    -0.23
    .setResult
    -0.23
    ä¼łéĹ»
    -0.23
    åĪ¶åº¦æĶ¹éĿ©
    -0.23
    POSITIVE LOGITS
    ana
    0.29
    aned
    0.28
    è´¨
    0.25
    ussen
    0.25
    好æľĭåıĭ
    0.25
    assador
    0.24
    ANA
    0.24
    æ°ij主åħļ
    0.24
    ACHE
    0.24
    support
    0.23
    Activations Density 0.123%

    No Known Activations

    This feature has no known activations.