© 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. 33478
    Prev
    Next
    INDEX
    Explanations

    jump from, jump to, jump high

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.10
    nement
    -0.09
    á»ıi
    -0.08
     ФС
    -0.08
     tắc
    -0.08
     sobÄħ
    -0.08
    chy
    -0.08
    иÑĤо
    -0.08
    umb
    -0.08
    ằn
    -0.08
    POSITIVE LOGITS
    èºį
    0.10
    frog
    0.09
    sters
    0.08
    elling
    0.08
    ingle
    0.08
    iness
    0.08
    è·³è·ĥ
    0.07
    骤
    0.07
    à¯ģà®ķ
    0.07
    ingly
    0.07
    Activations Density 0.028%

    No Known Activations