© 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. 5792
    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
    geries
    -0.29
    celed
    -0.27
    @author
    -0.27
    _chi
    -0.26
    è¾Ī
    -0.25
    ä¸Ģç¢Ĺ
    -0.25
    ="//
    -0.25
    -spacing
    -0.25
    erer
    -0.25
    çĤ¹åĩ»æŁ¥çľĭ
    -0.24
    POSITIVE LOGITS
    eki
    0.35
    ä¹Łå°Ĩ
    0.29
    _ATTACHMENT
    0.28
     terr
    0.27
    æĬķ
    0.26
    åħ¬åı¸å°Ĩ
    0.26
     Plum
    0.24
    ä»įå°Ĩ
    0.24
    QUI
    0.24
     prec
    0.23
    Activations Density 0.880%

    No Known Activations

    This feature has no known activations.