© 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. 22393
    Prev
    Next
    INDEX
    Explanations

    Caine, Jayhawks, Hololens, Paisleys

    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
    ibli
    -0.06
     diap
    -0.06
    åIJİèĩ³
    -0.06
    çİĭ建
    -0.06
    Sar
    -0.05
    ç¡®è¯ĬçĹħä¾ĭ
    -0.05
    èı²èı²
    -0.05
    grave
    -0.05
    æ¸ł
    -0.05
    version
    -0.05
    POSITIVE LOGITS
     spiagg
    0.08
    ÑĢож
    0.08
    anyol
    0.08
     nantinya
    0.08
    à§İ
    0.07
    ½Ķ
    0.07
    ÑĢÑĥÑĤ
    0.07
    <|box_end|>
    0.07
     Indah
    0.07
    åĽ½åħ¬
    0.07
    Activations Density 0.195%

    No Known Activations