© 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. 62910
    Prev
    Next
    INDEX
    Explanations

    fees and charges

    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
    rag
    -0.08
    rimp
    -0.08
    ught
    -0.07
    sofar
    -0.07
    æ´²
    -0.07
    ëĤĺë§Ī
    -0.07
    pector
    -0.07
    ustrial
    -0.07
    失æݪ
    -0.07
    auer
    -0.07
    POSITIVE LOGITS
    icient
    0.10
    ONTAL
    0.09
    ocious
    0.09
    ieux
    0.08
    ELLOW
    0.08
    ehren
    0.08
    idler
    0.08
    alties
    0.08
    iously
    0.08
    entially
    0.08
    Activations Density 0.014%

    No Known Activations