© 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. 8700
    Prev
    Next
    INDEX
    Explanations

    alone or instead

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.12
    <|box_end|>
    -0.12
    lässlich
    -0.09
    esi
    -0.09
    esub
    -0.08
    tw
    -0.08
     behalf
    -0.08
    zelf
    -0.08
    tre
    -0.08
    Ø©
    -0.08
    POSITIVE LOGITS
    æĪIJç«ł
    0.08
    quam
    0.08
    ftware
    0.07
    atson
    0.07
    arton
    0.07
     dÃłng
    0.07
    å¤ļè§ģ
    0.07
    اتÙģ
    0.07
    arahan
    0.07
    ا
    0.06
    Activations Density 0.001%

    No Known Activations