© 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. 5210
    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
     ranks
    -0.27
    vt
    -0.26
    IRS
    -0.25
    éĩĩ纳
    -0.25
    hn
    -0.24
    龸çİĭ
    -0.23
    isnan
    -0.23
     Action
    -0.23
     når
    -0.23
    VT
    -0.23
    POSITIVE LOGITS
    shortcut
    0.28
    (cli
    0.28
    æľ¨èĢ³
    0.26
    asser
    0.25
    åı¦
    0.25
    æ¼Ķ
    0.25
    åĪ¶
    0.25
     Routes
    0.24
    è½»æĿ¾
    0.24
     shortcut
    0.24
    Activations Density 0.033%

    No Known Activations

    This feature has no known activations.