© 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. 12951
    Prev
    Next
    INDEX
    Explanations

    words following punctuation

    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
    kees
    -0.09
    aed
    -0.09
    schau
    -0.09
    iscard
    -0.08
    pons
    -0.08
    umbs
    -0.08
     helicopt
    -0.08
    áĥĽáĥĺ
    -0.08
    ocket
    -0.08
    ç¥ŀåħ½
    -0.08
    POSITIVE LOGITS
    麽
    0.06
     pal
    0.06
    è¦ģä½ł
    0.06
    è¿ĻæŶ
    0.06
     fore
    0.06
     Palmer
    0.06
    ÏĦά
    0.06
     odl
    0.06
    åĪĨéħį
    0.06
     freaking
    0.05
    Activations Density 0.010%

    No Known Activations