© 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. 163158
    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
    åįģåħ«å±Ĭ
    -0.27
     spinning
    -0.25
     swinging
    -0.25
     axiom
    -0.25
     dynam
    -0.25
     rotating
    -0.25
     disclosed
    -0.24
    ystack
    -0.24
    =id
    -0.24
    cq
    -0.24
    POSITIVE LOGITS
     fiber
    0.29
    æĹĹ
    0.28
    flag
    0.27
    ä¿¡æģ¯æľįåĬ¡
    0.27
    fiber
    0.26
    stown
    0.26
    inform
    0.26
    .stamp
    0.25
     rơi
    0.25
     versa
    0.25
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.