© 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. 31173
    Prev
    Next
    INDEX
    Explanations

    figure out

    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
     sekali
    -0.07
    表çݰ为
    -0.07
    ÑıÑĤ
    -0.07
    ettel
    -0.07
    ential
    -0.06
    سة
    -0.06
    _validation
    -0.06
    imin
    -0.06
    resas
    -0.06
    -validator
    -0.06
    POSITIVE LOGITS
    æ¸ħæ¥ļ
    0.11
    éĢıå½»
    0.11
    å¼Ħæ¸ħæ¥ļ
    0.09
    å¼Ħæ¸ħ
    0.09
     anhand
    0.09
     оконÑĩаÑĤелÑĮно
    0.09
    éģķãģĦ
    0.08
    åĴĮçIJĨ解
    0.08
    æ¸ħæ¥ļäºĨ
    0.08
    æ¸ħæ¥ļçļĦ
    0.08
    Activations Density 0.147%

    No Known Activations