© 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. 3661
    Prev
    Next
    INDEX
    Explanations

    bloating, frequency, nausea, difficulty, pain

    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
    ovable
    -0.07
    çĶŁæŃ»
    -0.07
     theirs
    -0.07
    orthy
    -0.06
    æīģ
    -0.06
     weakest
    -0.06
    ç¼ĵåĨ²
    -0.06
    èĻļå¿ĥ
    -0.06
    ä¸įåIJĮæŶ
    -0.06
    岸
    -0.06
    POSITIVE LOGITS
    ä¼´æľī
    0.11
     palp
    0.09
    ä¼´éļıçĿĢ
    0.08
     accompanied
    0.08
    umento
    0.08
     disertai
    0.08
     âĵĺ
    0.08
    iculty
    0.08
    çŃīçĹĩçĬ¶
    0.08
     intense
    0.08
    Activations Density 0.101%

    No Known Activations