© 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. 10300
    Prev
    Next
    INDEX
    Explanations

    Marx, Try, advice, politics, messages, Diary, unbalance

    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
    ([(
    -0.08
    beck
    -0.07
    å¦Ĥæ½®
    -0.07
    å¦ĤåĽł
    -0.07
    _FREQ
    -0.07
    िति
    -0.07
    ×ķ×Ŀ
    -0.07
    emento
    -0.07
    γκα
    -0.07
    _FREQUENCY
    -0.07
    POSITIVE LOGITS
    -src
    0.07
    æĮ¨
    0.06
    -validator
    0.06
    æĸ°åŀĭåĨłçĬ¶çĹħæ¯ĴæĦŁæŁĵçļĦ
    0.06
    éĥ½æľīåı¯èĥ½
    0.06
    æķ£
    0.06
    åħĭåĬĽ
    0.06
    ifle
    0.06
    è´
    0.06
    онов
    0.06
    Activations Density 0.002%

    No Known Activations