© 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. 162370
    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
     insist
    -0.27
    æ§Į
    -0.26
    FieldValue
    -0.25
    åĶij
    -0.25
    .val
    -0.24
    uling
    -0.24
     dramas
    -0.24
    -val
    -0.24
    对ç«ĭ
    -0.24
    Ùħات
    -0.24
    POSITIVE LOGITS
    elho
    0.27
    urgeon
    0.27
    LinkId
    0.26
    IRM
    0.25
     breeding
    0.24
    红线
    0.24
    __,__
    0.24
    uously
    0.24
     LOD
    0.24
    ↵↵↵↵↵↵↵
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.