© 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. 61288
    Prev
    Next
    INDEX
    Explanations

    numbers and identifiers

    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
    ustu
    -0.08
    à¹Ģà¸Ħร
    -0.07
    oge
    -0.07
    ieties
    -0.07
    emma
    -0.07
    طة
    -0.07
    _except
    -0.07
    _HEL
    -0.07
    注æĦıçĤ¹
    -0.07
    gia
    -0.07
    POSITIVE LOGITS
    .exports
    0.07
    urz
    0.07
    å½ĵå¹´çļĦ
    0.07
    çĻ¾äºĭ
    0.06
    @
    0.06
    èĪľ
    0.06
    roken
    0.06
     Bryant
    0.06
     indent
    0.06
    ur
    0.06
    Activations Density 0.117%

    No Known Activations