© 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. 8587
    Prev
    Next
    INDEX
    Explanations

    no problem

    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
    er
    -0.08
    vertise
    -0.08
    æľªåħį
    -0.07
    ä¸įåħį
    -0.07
    iffer
    -0.07
    leigh
    -0.07
    iard
    -0.07
    erdo
    -0.07
    erse
    -0.07
    Notify
    -0.07
    POSITIVE LOGITS
    ¿
    0.08
    chia
    0.08
    assin
    0.08
     xuôi
    0.08
    Ø©
    0.08
    -going
    0.08
    ness
    0.08
    ably
    0.08
    chio
    0.08
    except
    0.07
    Activations Density 0.003%

    No Known Activations