© 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. 39963
    Prev
    Next
    INDEX
    Explanations

    –and

    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
    ìį¨
    -0.17
    <|box_end|>
    -0.13
    Ø©
    -0.12
    ness
    -0.12
    çĦ¶å¤§
    -0.11
    à¯įà®ķ
    -0.11
    Äĥ
    -0.11
    IMUM
    -0.11
    Ùij
    -0.11
     ÐĶополни
    -0.11
    POSITIVE LOGITS
    ,
    0.09
    :
    0.08
    al
    0.08
    åħ¶
    0.08
    .
    0.07
    ...
    0.07
    ments
    0.07
    æĸ°åĬłåĿ¡
    0.07
    e
    0.07
    ìļĶ
    0.07
    Activations Density 0.008%

    No Known Activations