© 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. 31235
    Prev
    Next
    INDEX
    Explanations

    .log file path or test cases

    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
    %f
    -0.08
    ÙĦاس
    -0.07
    å½ĵåħ¶
    -0.07
    chow
    -0.07
    ))).
    -0.07
    ائÙĩا
    -0.07
    ober
    -0.07
    enha
    -0.07
    ìĪľ
    -0.07
    ++.
    -0.06
    POSITIVE LOGITS
     alast
    0.07
    æ¼Ĥ
    0.06
    æİ©
    0.06
     Malk
    0.06
    ÑĢиз
    0.06
    äºĨä¸įèµ·
    0.06
    uiltin
    0.06
    åį±
    0.06
    æĺĶ
    0.06
    åħ®
    0.06
    Activations Density 0.027%

    No Known Activations