© 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. 7872
    Prev
    Next
    INDEX
    Explanations

    `/** @param {String|Array|Function|value}`

    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
    æħµ
    -0.08
    quelle
    -0.07
    EXTERN
    -0.07
    åħįè´¹æıIJä¾Ľ
    -0.07
    使çĶ¨æĸ¹ä¾¿
    -0.07
    !),
    -0.07
    gaard
    -0.07
    .observable
    -0.07
    aley
    -0.07
    _locals
    -0.07
    POSITIVE LOGITS
    -ish
    0.08
    æĪĸå¤ļ
    0.07
    ersey
    0.07
    .addTo
    0.07
    ยà¹Į
    0.07
    ä¹İ
    0.06
    æĨ¾
    0.06
    æľºåħ³
    0.06
    |
    0.06
    å®ŀå½ķ
    0.06
    Activations Density 0.016%

    No Known Activations