© 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. 63728
    Prev
    Next
    INDEX
    Explanations

    difference between

    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
    gether
    -0.10
    ¤
    -0.09
    Ñģловно
    -0.09
    postav
    -0.09
     ulang
    -0.08
    eram
    -0.08
    niec
    -0.08
    pjes
    -0.08
    å§ĭèĩ³ç»Ī
    -0.08
    å©·
    -0.08
    POSITIVE LOGITS
    ing
    0.09
    æĤ¬æ®Ĭ
    0.09
    /add
    0.09
    iculty
    0.08
    iating
    0.08
    ERENCE
    0.08
    lessly
    0.08
    ials
    0.08
    ingly
    0.07
     between
    0.07
    Activations Density 0.032%

    No Known Activations