© 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. 87931
    Prev
    Next
    INDEX
    Explanations

    Medical studies

    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
     bern
    -0.26
     almost
    -0.26
    æĸ°çļĦä¸Ģ
    -0.26
    fest
    -0.25
    CEE
    -0.24
    issor
    -0.24
     Uniform
    -0.24
    æĸ°æĹ¶æľŁ
    -0.24
     exclusively
    -0.24
    itor
    -0.23
    POSITIVE LOGITS
    azes
    0.25
    ä¸ķ
    0.25
    èĴ¸
    0.25
    ä½ĵèĤ²é¦Ĩ
    0.24
    _race
    0.24
    łéĻ¤
    0.23
    ç§įæĹı
    0.23
     Race
    0.23
    uffs
    0.23
    èµĸ
    0.23
    Activations Density 0.032%

    No Known Activations