© 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. 163355
    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
    ickness
    -0.30
    é»ij马
    -0.28
    alah
    -0.27
    å¹²ç»Ĩèĥŀ
    -0.26
    пÑĥÑģка
    -0.25
     Lö
    -0.25
    /domain
    -0.25
    iac
    -0.25
    å¾Ĺèµ·
    -0.25
     (++
    -0.24
    POSITIVE LOGITS
    é¢IJ
    0.27
    åħ·ä½ĵæĥħåĨµ
    0.26
    arching
    0.26
    .Marshal
    0.25
     controls
    0.24
    quila
    0.24
    quake
    0.24
    hid
    0.24
    ä¿¡èµĸ
    0.24
    åħħ足çļĦ
    0.23
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.