© 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. 22138
    Prev
    Next
    INDEX
    Explanations

    topology, restricted, getClassLoader

    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
     anonyme
    -0.08
    iete
    -0.07
    bsub
    -0.07
     anonym
    -0.07
    åĩĢ
    -0.07
    #index
    -0.07
    æ·¨
    -0.07
    ocard
    -0.07
    æ±łä¸Ń
    -0.07
    ħ
    -0.07
    POSITIVE LOGITS
     restricted
    0.07
    ä¸Ģå±Ĥ
    0.07
    çķı
    0.07
    pered
    0.07
    restrict
    0.07
     restrict
    0.06
     restrictions
    0.06
    秩
    0.06
    æĶ¯éħį
    0.06
    å½¢æĪIJçļĦ
    0.06
    Activations Density 0.009%

    No Known Activations