© 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. 87218
    Prev
    Next
    INDEX
    Explanations

    Leadership titles

    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»
    -0.28
    ä¹Łåıªèĥ½
    -0.27
    ronym
    -0.27
    vehicles
    -0.27
    éĩįåŀĭ
    -0.26
     duże
    -0.26
    ä¸Ĭåİ»
    -0.26
    bserv
    -0.26
    robat
    -0.26
    课é¢ĺ
    -0.26
    POSITIVE LOGITS
    ê²IJ
    0.25
    é£İåħī
    0.25
     zie
    0.25
    Boy
    0.24
     policing
    0.23
     ceremonies
    0.23
    ulti
    0.23
    æ¯ĭ
    0.23
    .scene
    0.23
    对æİ¥
    0.23
    Activations Density 0.030%

    No Known Activations