© 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. 42178
    Prev
    Next
    INDEX
    Explanations

    dating websites

    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
    ban
    -0.08
    ad
    -0.07
    al
    -0.06
    å¯Ĥ
    -0.06
    h
    -0.06
    ste
    -0.06
    æķ´
    -0.06
    ou
    -0.06
    èŁ¹
    -0.06
    ç´§
    -0.05
    POSITIVE LOGITS
    ìĪ
    0.09
    impa
    0.09
    è·¯éĢı
    0.09
    রà§įণ
    0.09
    omba
    0.09
    abouts
    0.08
    deÅŁ
    0.08
    大åħ¨
    0.08
    resco
    0.08
    ertest
    0.08
    Activations Density 0.001%

    No Known Activations