© 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. 31846
    Prev
    Next
    INDEX
    Explanations

    comment markers

    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
    isia
    -0.07
    ิà¸ķิ
    -0.07
    ä¸įä¸ĭ
    -0.07
    andel
    -0.07
    andle
    -0.07
    å®ŀ
    -0.06
    èĩªä¸»
    -0.06
    rial
    -0.06
    åħµåĻ¨
    -0.06
    éĺ²
    -0.06
    POSITIVE LOGITS
    éĵ¶å±±
    0.07
    à¹Ģวียà¸Ļ
    0.07
    èĽŁ
    0.06
    æĹĹé¼ĵ
    0.06
    -)
    0.06
    OPSIS
    0.06
    Ïģαι
    0.06
    çīĪæĿĥçŃī
    0.06
    asseur
    0.06
    æµ·è§Ĵ
    0.06
    Activations Density 0.036%

    No Known Activations