© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7431
    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
    igr
    -0.27
     stripe
    -0.25
    çĪ°
    -0.24
    æµ·åı£
    -0.24
    arah
    -0.24
    formance
    -0.23
     morality
    -0.23
    åħ¨å®¶
    -0.23
    表
    -0.23
    ilateral
    -0.23
    POSITIVE LOGITS
    лÑĮÑĨ
    0.27
    èĸ¨
    0.25
    ÑģÑı
    0.23
    éĮ¯
    0.23
    éĶĻ
    0.23
    享åıĹ
    0.23
     *(*
    0.23
    ä¸įè§ģ
    0.23
    èĭ¥æĤ¨
    0.23
    ·»
    0.23
    Activations Density 0.127%

    No Known Activations

    This feature has no known activations.