© 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. 5279
    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
    ÑĢеÑģÑĤ
    -0.26
    æĪijçļĦå¿ĥ
    -0.25
     confident
    -0.25
    /fixtures
    -0.25
    å¿ħçĦ¶
    -0.25
     çek
    -0.25
     RAW
    -0.24
    å¿Ļç¢Į
    -0.24
    [])č↵
    -0.24
    encers
    -0.23
    POSITIVE LOGITS
     subsidi
    0.30
    oss
    0.29
     pint
    0.28
    icker
    0.27
    oldt
    0.25
    pmat
    0.25
     spoiler
    0.25
    PUR
    0.24
    STACK
    0.24
    airo
    0.24
    Activations Density 0.129%

    No Known Activations

    This feature has no known activations.