© 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. 19-TRANSCODER-HP
    7. 8568
    Prev
    Next
    INDEX
    Explanations

    problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     missed
    -0.33
     polish
    -0.28
    icap
    -0.28
    raud
    -0.27
     اÙĦÙĦÙĩ
    -0.26
     overlook
    -0.25
    æ´Ļ
    -0.24
     underrated
    -0.23
    éģĹæ¼ı
    -0.23
    liest
    -0.23
    POSITIVE LOGITS
    çİ°åľ¨å¾Īå¤ļ
    0.26
    éĤ¸
    0.26
    äºĭåĬ¡
    0.26
    ureen
    0.25
     displaying
    0.25
    ç¯Ŀ
    0.25
    display
    0.25
    athom
    0.24
    emplate
    0.24
    ssel
    0.24
    Activations Density 0.016%

    No Known Activations