© 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. 1232
    Prev
    Next
    INDEX
    Explanations

    c code headers

    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
    inne
    -0.08
    溢
    -0.07
    urd
    -0.07
    inki
    -0.07
    utherford
    -0.07
     csrf
    -0.07
    å·¥ç¨ĭçŃī
    -0.07
    æľ¬æĿ¥å°±
    -0.07
    .databinding
    -0.07
    åĩłä¸ĭ
    -0.07
    POSITIVE LOGITS
    иÑĩ
    0.08
    åıĹåĪ°
    0.07
    èĭĹ
    0.07
    æIJŀ
    0.07
    &S
    0.06
    FU
    0.06
    mess
    0.06
    xn
    0.06
    çĥ½
    0.06
    vil
    0.06
    Activations Density 0.468%

    No Known Activations