© 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. 60246
    Prev
    Next
    INDEX
    Explanations

    code blocks with semicolons

    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
    гови
    -0.08
    icket
    -0.08
    iley
    -0.07
    ηÏĥη
    -0.07
    ötz
    -0.07
    使å®ĥ
    -0.07
    -inspired
    -0.07
     Schles
    -0.07
    ç¨ĭ
    -0.07
    å¼Ĥ彩
    -0.06
    POSITIVE LOGITS
    ria
    0.07
    å°ıå¿ĥç¿¼ç¿¼åľ°
    0.07
    éľĨ
    0.07
    rn
    0.06
    èĥ½èĢĹ
    0.06
     cias
    0.06
    æīĵçģ«
    0.06
    å°Ķå¤ļ
    0.06
    å¿ĥçĹħ
    0.06
    alf
    0.06
    Activations Density 0.036%

    No Known Activations