© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98911
    Prev
    Next
    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     time
    -0.31
     internally
    -0.30
     initially
    -0.29
    InSection
    -0.29
    scoped
    -0.28
     limits
    -0.27
    çľĭå¾ħ
    -0.27
     some
    -0.26
     sometimes
    -0.26
     greatest
    -0.26
    POSITIVE LOGITS
    è£ħ
    0.29
    LAG
    0.29
    åIJį
    0.27
    æ°¸è¿ľä¸įä¼ļ
    0.27
    eshire
    0.27
    åIJįæł¡
    0.26
    ä»İæľª
    0.26
    idis
    0.25
    æ°¸è¿ľ
    0.25
     Biological
    0.25
    Activations Density 0.002%

    No Known Activations