© 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. 163166
    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
    antha
    -0.26
    æľĭ
    -0.26
    ä¸Ģå°ģä¿¡
    -0.25
    quir
    -0.25
    anth
    -0.25
    .fail
    -0.24
     blames
    -0.24
    otch
    -0.24
     fav
    -0.24
    IBC
    -0.24
    POSITIVE LOGITS
    mares
    0.27
    aways
    0.26
    brid
    0.26
    ons
    0.24
     keyPressed
    0.24
    æĹ¥å¤ľ
    0.23
    âĮ¨
    0.23
    çģ«çĥ§
    0.23
     McKay
    0.23
    èµ°åľ¨
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.