© 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. 34113
    Prev
    Next
    INDEX
    Explanations

    Compound nouns and specific terms

    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
    Âł
    -0.07
    éĥ
    -0.06
    ัà¸ģ
    -0.06
    ä¸Ģç¬ij
    -0.06
    ingers
    -0.06
    -0.06
    _kw
    -0.05
    ç´Ķ
    -0.05
    MO
    -0.05
    £
    -0.05
    POSITIVE LOGITS
    trak
    0.08
    .misc
    0.08
    .tk
    0.08
    raub
    0.08
    åı²ä¸ĬæľĢ
    0.08
    ).__
    0.08
    ầm
    0.08
    _DIALOG
    0.08
    enville
    0.08
    æĶ¹éĿ©åıijå±ķ
    0.08
    Activations Density 0.021%

    No Known Activations