© 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. 39528
    Prev
    Next
    INDEX
    Explanations

    clinical and scientific contexts

    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
    Õ©
    -0.09
    éģ®
    -0.09
    -await
    -0.08
    protocols
    -0.08
    ahui
    -0.08
    tere
    -0.07
    _requires
    -0.07
     scopes
    -0.07
    åijĽ
    -0.07
    venues
    -0.07
    POSITIVE LOGITS
     bonus
    0.08
     bonuses
    0.07
     penalties
    0.07
    项
    0.07
    å¹³æ»ij
    0.07
    åĨ·
    0.07
     anomaly
    0.07
    wap
    0.07
     strength
    0.07
    ä»ĩ
    0.07
    Activations Density 0.002%

    No Known Activations