© 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. 19-TRANSCODER-HP
    7. 5427
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oct
    -0.26
    åĪ©æ¶¦çİĩ
    -0.26
    ective
    -0.26
    ONSE
    -0.26
    ocr
    -0.25
     overlap
    -0.25
     Oct
    -0.25
    Indented
    -0.24
    秣
    -0.24
     Mü
    -0.24
    POSITIVE LOGITS
    INGTON
    0.32
    ington
    0.28
    arl
    0.27
     Liber
    0.26
    Cele
    0.26
    æľªç»ıæİĪæĿĥ
    0.25
    term
    0.25
    ’Ãł
    0.25
    enen
    0.24
    /sbin
    0.24
    Activations Density 0.137%

    No Known Activations

    This feature has no known activations.