© 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. 88621
    Prev
    Next
    INDEX
    Explanations

    Months and days

    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
    ellar
    -0.27
    å¹
    -0.25
    apple
    -0.24
    æ±°
    -0.24
    PIP
    -0.24
     slut
    -0.23
    äsent
    -0.23
    åĽł
    -0.23
    åľ¨æĪijåĽ½
    -0.23
    artner
    -0.23
    POSITIVE LOGITS
    gons
    0.28
    éĴ¡
    0.28
    iasm
    0.27
    å»¶æľŁ
    0.27
    èĨº
    0.26
    å¤ĸéĿ¢
    0.25
    ersion
    0.25
    asure
    0.25
    mez
    0.25
    æĭħ
    0.24
    Activations Density 0.011%

    No Known Activations