© 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. 39593
    Prev
    Next
    INDEX
    Explanations

    Theaster Shelton et al., Plaintiff-Appellee

    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
    sched
    -0.08
    ä¸ĭå¿ĥ
    -0.07
    好åķĬ
    -0.07
    ilion
    -0.07
    asseur
    -0.07
     yrs
    -0.06
    ä¸ĭè§Ĵ
    -0.06
    ä¹ĭæķ°
    -0.06
    äºĨä¸ĭ
    -0.06
    èIJ½äºİ
    -0.06
    POSITIVE LOGITS
    åı·éĻ¢
    0.07
    åľ°äºļ
    0.07
    º
    0.06
    apphire
    0.06
    voke
    0.06
    alba
    0.06
    Handlers
    0.06
    æīįèĥ½å¤Ł
    0.06
    zinho
    0.06
    elat
    0.06
    Activations Density 0.180%

    No Known Activations