© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17120
    Prev
    Next
    INDEX
    Explanations

    Generated by class-dump

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ial
    -0.07
    iras
    -0.07
    indari
    -0.07
    ially
    -0.06
    zend
    -0.06
    postData
    -0.06
    emain
    -0.06
    isata
    -0.06
    udeau
    -0.06
    ":-
    -0.06
    POSITIVE LOGITS
    auc
    0.08
    maak
    0.08
    æĸ°æ°ij
    0.08
    æĸ°åĬŁèĥ½
    0.07
    迹
    0.07
    æĸ°å¼Ģ
    0.07
    æĬĽ
    0.07
    ouvre
    0.07
    뼰
    0.07
    acre
    0.07
    Activations Density 0.100%

    No Known Activations