© 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. 30753
    Prev
    Next
    INDEX
    Explanations

    suit King Ace

    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
    es
    -0.07
    abay
    -0.07
    ows
    -0.07
    人åı£æĻ®æŁ¥
    -0.06
    combe
    -0.06
    æ°Ķåİĭ
    -0.06
    ijľ
    -0.06
    è¤Ĵ
    -0.06
     "<<
    -0.06
    echt
    -0.06
    POSITIVE LOGITS
    imbra
    0.08
    ëĭ¥
    0.08
    stype
    0.08
    channels
    0.07
    cind
    0.07
    stat
    0.07
    errupted
    0.07
    áŀĦ
    0.07
     bó
    0.07
    saus
    0.07
    Activations Density 0.002%

    No Known Activations