© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23183
    Prev
    Next
    INDEX
    Explanations

    long / require / have / supplied

    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
    اشت
    -0.08
    å·§
    -0.08
    çĶļèĩ³è¿ŀ
    -0.08
    ×Ĺ×Ļ
    -0.07
    çĶļèĩ³è¿ĺ
    -0.07
    phones
    -0.07
    ÏĨÏĮ
    -0.07
    até
    -0.07
    å¦Ŀ
    -0.07
    é¦ĸ度
    -0.07
    POSITIVE LOGITS
    MDB
    0.07
    çĮľä½łåĸľæ¬¢
    0.07
    zeb
    0.06
    achs
    0.06
    jo
    0.06
    @
    0.06
     allo
    0.06
    ieten
    0.06
     relent
    0.06
    èį·
    0.06
    Activations Density 0.002%

    No Known Activations