© 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. 25840
    Prev
    Next
    INDEX
    Explanations

    second or part

    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
    atina
    -0.08
    æĹ©
    -0.08
    åĢĻ
    -0.07
    èĺij
    -0.07
    lio
    -0.07
    igid
    -0.06
    å¿ħåħĪ
    -0.06
    ukke
    -0.06
    ngo
    -0.06
    .ReadAll
    -0.06
    POSITIVE LOGITS
    次äºİ
    0.08
    ç´§æİ¥çĿĢ
    0.08
    Secondary
    0.08
    次çļĦ
    0.07
    elper
    0.07
    secondary
    0.07
    (second
    0.07
    ละ
    0.07
    åıĺæĽ´é¡¹çĽ®
    0.07
    -feira
    0.07
    Activations Density 0.325%

    No Known Activations