© 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. 87081
    Prev
    Next
    INDEX
    Explanations

    Programming code

    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
    ä¸Ĭåİ»
    -0.32
     dise
    -0.29
    èµ°åĩºæĿ¥
    -0.29
    ä¸įèĥ½åĨį
    -0.27
    转载请
    -0.26
    ä¹Łå¸ĮæľĽ
    -0.26
    èĮ¸
    -0.25
    éĤ£æł·çļĦ
    -0.25
     assume
    -0.24
    åĢĴå¡Į
    -0.24
    POSITIVE LOGITS
    rox
    0.26
    éĻĦåĬł
    0.26
    æľ¬è½®
    0.26
    icit
    0.25
    æĬ¥
    0.25
    apt
    0.24
    ben
    0.23
    æľīå¤ļ
    0.23
    etr
    0.23
     flats
    0.23
    Activations Density 0.017%

    No Known Activations