© 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. 5901
    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
    ä»İèĢĮ
    -0.28
     thereby
    -0.27
    ny
    -0.26
    dm
    -0.26
    _CONFIGURATION
    -0.25
    uft
    -0.25
    -bal
    -0.24
    å¼ĢéĢļ
    -0.24
    DM
    -0.24
    æµİ
    -0.24
    POSITIVE LOGITS
     Shed
    0.27
    åľ¨ä»ĸçļĦ
    0.27
     cellpadding
    0.27
    (ca
    0.26
    gota
    0.26
    stery
    0.26
    stress
    0.26
    vider
    0.26
     cref
    0.26
    è¿ĻäºĽéĹ®é¢ĺ
    0.26
    Activations Density 0.831%

    No Known Activations

    This feature has no known activations.