© 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. 162654
    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
     hinge
    -0.28
    çľĭä¼¼
    -0.26
     {*
    -0.25
    åºķæ°Ķ
    -0.25
    endors
    -0.24
    stitución
    -0.24
    igt
    -0.23
     lo
    -0.23
    endale
    -0.23
    åĮ£
    -0.23
    POSITIVE LOGITS
    enschaft
    0.29
    .opend
    0.26
    plr
    0.25
     ;-)
    0.24
    dac
    0.24
    _tid
    0.23
    èĤ¥èĥĸ
    0.23
    hte
    0.23
    aho
    0.23
    oud
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.