© 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. 129953
    Prev
    Next
    INDEX
    Explanations

    Actions, doing things

    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
     Calls
    -0.26
    -call
    -0.25
    elog
    -0.24
    å°¢
    -0.23
    ankan
    -0.23
    enton
    -0.23
    озвÑĢаÑī
    -0.23
    anked
    -0.22
    åIJĮç±»
    -0.22
    è¿ijäºĽ
    -0.22
    POSITIVE LOGITS
    zia
    0.26
    aments
    0.26
    née
    0.24
    家åºŃ
    0.24
    ÑĢма
    0.24
     pant
    0.24
    PEC
    0.23
    ä¼ļä¸Ĭ
    0.23
    unction
    0.23
    导èĪª
    0.23
    Activations Density 0.007%

    No Known Activations