© 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. 112767
    Prev
    Next
    INDEX
    Explanations

    Phone numbers

    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
    ccording
    -0.31
    è´Ŀå°Ķ
    -0.28
    éĢı
    -0.28
     according
    -0.27
    deal
    -0.27
     ÐijолÑĮÑĪ
    -0.26
     footsteps
    -0.25
     beet
    -0.25
     importance
    -0.25
     cánh
    -0.25
    POSITIVE LOGITS
    abı
    0.27
    æľ¬æĬ¥
    0.26
    å¯ĩ
    0.26
    lify
    0.25
    åĴĮ个人
    0.25
    æĥ³çĿĢ
    0.25
    Grace
    0.24
    JV
    0.24
     Tmin
    0.24
    pard
    0.24
    Activations Density 0.022%

    No Known Activations