© 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. 23300
    Prev
    Next
    INDEX
    Explanations

    I was

    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
    ullet
    -0.08
     '
    -0.08
    .baidu
    -0.07
    æ´
    -0.07
    ov
    -0.06
    å¼Ĥ
    -0.06
    iere
    -0.06
    ille
    -0.06
     '.',
    -0.06
    ict
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.09
    꽤
    0.08
    _DECLARE
    0.07
    inan
    0.07
    ×Ĺק
    0.07
    åıĬ使çĶ¨
    0.07
    izzo
    0.07
    yanto
    0.07
    лÑĮмо
    0.07
     INTEG
    0.07
    Activations Density 0.215%

    No Known Activations