© 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. 40421
    Prev
    Next
    INDEX
    Explanations

    challenges and advances

    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
    aims
    -0.08
    失äºĨ
    -0.07
    ä»İèĢĮæıIJé«ĺ
    -0.07
    rape
    -0.07
    itants
    -0.07
    _FAILURE
    -0.07
    以éĢĤåºĶ
    -0.07
    åį·
    -0.07
    pls
    -0.07
    çļĦåIJĹ
    -0.07
    POSITIVE LOGITS
    使å¾Ĺ
    0.10
     باعث
    0.09
    使æĪij们
    0.08
     sprawia
    0.08
    çŃīåĽłç´ł
    0.08
     makes
    0.08
    æĥħåĨµè¯´æĺİ
    0.08
     à¸Ĺำà¹ĥหà¹ī
    0.08
    å°±æĺ¯æľĢ好çļĦ
    0.08
    åĬłä¸Ĭ
    0.08
    Activations Density 0.356%

    No Known Activations