© 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. 46965
    Prev
    Next
    INDEX
    Explanations

    modelselection, testing, compared, restricted models

    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
    ç¼Ī
    -0.08
    æĥ³ä¸Ģæĥ³
    -0.06
    rau
    -0.06
    ãĥ©ãĥªãĥ¼
    -0.06
    antine
    -0.06
     supply
    -0.06
    raga
    -0.06
    бой
    -0.06
    éĵ¶å¹ķ
    -0.06
     startX
    -0.06
    POSITIVE LOGITS
    ienst
    0.09
    大æ³ķ
    0.08
    罪
    0.08
     goodness
    0.08
    ×ķ×ĵ×Ķ
    0.07
    Score
    0.07
     pars
    0.07
    riterion
    0.07
    Criterion
    0.07
     Score
    0.07
    Activations Density 0.004%

    No Known Activations