© 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. 9975
    Prev
    Next
    INDEX
    Explanations

    print edition, general population, natural language

    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
    quate
    -0.08
    ements
    -0.08
    sher
    -0.07
    cerer
    -0.07
    posites
    -0.07
    ibaldi
    -0.07
    IMIT
    -0.07
    亲æľĭ
    -0.07
    hoven
    -0.07
    IMI
    -0.07
    POSITIVE LOGITS
    tn
    0.08
    isis
    0.07
    æŬ
    0.07
     maupun
    0.07
    aws
    0.07
    ziel
    0.07
     vs
    0.07
    rame
    0.06
    èģĶç³»
    0.06
    èĪ
    0.06
    Activations Density 0.642%

    No Known Activations