© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130834
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    bero
    -0.30
     Reserve
    -0.30
    даÑĩи
    -0.28
    reserve
    -0.26
     reserve
    -0.26
    isque
    -0.26
    æľīä¸ĢçĤ¹
    -0.25
    .bel
    -0.25
    æķ£
    -0.24
     overwhelmingly
    -0.24
    POSITIVE LOGITS
    èĤļ
    0.29
    icut
    0.27
     Grab
    0.27
    æ¦Ķ
    0.26
     ìľĦíķ´ìĦľ
    0.25
     wes
    0.25
    çķľ
    0.24
    åĽ½åĬ¡
    0.24
    Grab
    0.24
     openings
    0.24
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.