© 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. 41615
    Prev
    Next
    INDEX
    Explanations

    inquiries and next steps

    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
    ibel
    -0.08
    ./.
    -0.08
    way
    -0.08
    åªĴ
    -0.08
    dda
    -0.08
    quier
    -0.08
    å¹´å§ĭ
    -0.08
    зам
    -0.07
    ÑģиÑĤ
    -0.07
    .realpath
    -0.07
    POSITIVE LOGITS
    è¶Ĭ
    0.07
    çĻ¾
    0.07
     Vaughan
    0.06
    èĮħ
    0.06
    èī¾
    0.06
    æľº
    0.06
    æĬĺ
    0.06
    éĢļ
    0.06
    atter
    0.06
    è¿Ľ
    0.06
    Activations Density 1.671%

    No Known Activations