© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51054
    Prev
    Next
    INDEX
    Explanations

    explanation of rights

    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
     Présent
    -0.08
    çĸĻ
    -0.08
    arence
    -0.07
    ussy
    -0.07
    глÑıд
    -0.07
    rego
    -0.07
    iras
    -0.07
    ansa
    -0.07
    ISH
    -0.07
    icas
    -0.07
    POSITIVE LOGITS
    éĿ¢æĹł
    0.08
    ervers
    0.06
    ToFit
    0.06
    ä¸įæĥĬ
    0.06
    amedi
    0.06
    Untitled
    0.06
    çĨı
    0.06
    èĬ½
    0.06
    ¡´
    0.06
    NOP
    0.06
    Activations Density 0.073%

    No Known Activations