© 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. 162383
    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
     arriving
    -0.29
    combe
    -0.27
     Riot
    -0.27
    大æĪĺ
    -0.26
    Breaking
    -0.25
    ìĤ¬ë¬´
    -0.25
     %"
    -0.24
     arrived
    -0.24
    COPY
    -0.24
    çľĭåĪ°äºĨ
    -0.23
    POSITIVE LOGITS
    dbuf
    0.30
    inea
    0.25
    åħ¥å¸Ĥ
    0.25
     unb
    0.25
    æł·
    0.25
    dfa
    0.25
    ulings
    0.24
    dac
    0.24
    –and
    0.24
    ÃĩÃĥO
    0.24
    Activations Density 0.028%

    No Known Activations

    This feature has no known activations.