© 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. 65256
    Prev
    Next
    INDEX
    Explanations

    from [number]

    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
    ole
    -0.07
    ([...
    -0.07
    以德
    -0.06
    è¿Ľä¸ĢæŃ¥åıijå±ķ
    -0.06
    Įĵ
    -0.06
    stwo
    -0.06
    aul
    -0.06
    ette
    -0.06
    ohn
    -0.06
    çļĦæľĢ大
    -0.06
    POSITIVE LOGITS
    èIJ¤çģ«
    0.08
    verz
    0.08
    åįĹèĩ³
    0.08
     ?,
    0.08
    çĶ·ç¥ŀ
    0.07
    ulary
    0.07
    вали
    0.07
    issons
    0.07
    erson
    0.07
    ÐĶУ
    0.07
    Activations Density 0.009%

    No Known Activations