© 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. 5392
    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
    allas
    -0.28
    zilla
    -0.28
    thane
    -0.27
    oola
    -0.27
    ixo
    -0.25
     Profile
    -0.25
     лиÑĩно
    -0.24
    ä¿¡ä»»
    -0.24
    instr
    -0.24
    rama
    -0.24
    POSITIVE LOGITS
    /ui
    0.27
    çĺ¸
    0.25
    ¶ļ
    0.24
    å¾ģæ±Ĥ
    0.24
    èĢĮçİ°åľ¨
    0.24
    _bulk
    0.24
    æŁIJç§į
    0.24
    åģľå·¥
    0.24
    ĽĦ
    0.24
    ä¸į让
    0.24
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.