© 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. 112845
    Prev
    Next
    INDEX
    Explanations

    other

    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
     dreaded
    -0.25
    propri
    -0.24
    pees
    -0.24
    æ¹ĸ
    -0.24
    monic
    -0.23
    è¯Ŀ
    -0.23
    äch
    -0.23
    å¤©åľ°
    -0.23
    :not
    -0.23
    perature
    -0.23
    POSITIVE LOGITS
    .Companion
    0.27
    类似
    0.27
    åľ¨çº¿åĴ¨è¯¢
    0.25
    ä¿İ
    0.25
    erot
    0.24
    类似çļĦ
    0.24
    èĥ½è¾¾åĪ°
    0.24
    ãģĤãĤĬãģ¾ãģĻãģĮ
    0.24
    åIJĮç±»
    0.24
    âĢ¢↵↵
    0.23
    Activations Density 0.006%

    No Known Activations