© 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. 38246
    Prev
    Next
    INDEX
    Explanations

    Available, way, flow, Alone, In, Own

    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
    oland
    -0.08
    çļĦè¿Ļç§į
    -0.08
    /../
    -0.07
    æľīçļĦæŶåĢĻ
    -0.07
    oller
    -0.07
    ents
    -0.07
    æķħåIJį
    -0.07
    )?.
    -0.07
    ail
    -0.07
    &D
    -0.07
    POSITIVE LOGITS
    igung
    0.07
    adius
    0.07
    ฯ
    0.07
    tür
    0.06
    enticate
    0.06
    âĢİ
    0.06
    æĪĸåĪłéĻ¤
    0.06
    à¸Ļà¹Į
    0.06
     séc
    0.06
    fet
    0.06
    Activations Density 0.045%

    No Known Activations