© 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. 43310
    Prev
    Next
    INDEX
    Explanations

    inquiry or drift

    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
    ecess
    -0.10
    åĸ·æ¼Ĩ
    -0.08
    ibal
    -0.08
     oportun
    -0.08
    åħ¸
    -0.08
    ç»ĻåŃ©åŃIJ们
    -0.08
    ensee
    -0.08
     necess
    -0.08
    èĩŃ
    -0.08
    masked
    -0.07
    POSITIVE LOGITS
     consciously
    0.11
     conscious
    0.10
     meditation
    0.10
     mindfulness
    0.09
    è§īå¯Ł
    0.09
     repetitions
    0.09
    æĦıè¯Ĩåľ°
    0.08
     awareness
    0.08
     Meditation
    0.08
    æĦı念
    0.08
    Activations Density 0.021%

    No Known Activations