© 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. 39293
    Prev
    Next
    INDEX
    Explanations

    look closely

    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
    ardini
    -0.10
    szt
    -0.10
    ÏĨÏĮ
    -0.09
    AGER
    -0.09
    creenshot
    -0.09
    æv
    -0.09
    <|box_end|>
    -0.09
    lific
    -0.09
    à§Ģয়
    -0.09
    缴æݥ被
    -0.09
    POSITIVE LOGITS
    åħ¥å¾®
    0.08
     enough
    0.08
    lates
    0.07
    es
    0.07
    al
    0.06
    ity
    0.06
    çľĭä¸į
    0.06
    ãģªãģĮãĤī
    0.06
    è¿ĩ头
    0.06
    ,
    0.06
    Activations Density 0.001%

    No Known Activations