© 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. 112474
    Prev
    Next
    INDEX
    Explanations

    People's backgrounds and careers

    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¸ĢéĿ¢
    -0.28
    Monday
    -0.27
    åī¯ç§ĺ书éķ¿
    -0.27
    æĺİæĹ¥
    -0.27
     staffers
    -0.26
    Tuesday
    -0.25
    åºĹåĨħ
    -0.25
    åģľçīĮ
    -0.25
    éĢīåĩº
    -0.25
    лÑİд
    -0.24
    POSITIVE LOGITS
    isory
    0.29
    翳
    0.28
    ylv
    0.27
    umbing
    0.25
    arus
    0.25
    Rh
    0.25
    _DU
    0.24
    IOD
    0.24
    äºĮåįģå¹´
    0.24
     Zus
    0.24
    Activations Density 0.007%

    No Known Activations