© 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. 11229
    Prev
    Next
    INDEX
    Explanations

    starts section or lists

    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
    ney
    -0.08
    害
    -0.07
    ous
    -0.07
    nÃŃ
    -0.06
    us
    -0.06
    ities
    -0.06
    æ¥ļ
    -0.06
    ling
    -0.06
    onia
    -0.06
    anh
    -0.06
    POSITIVE LOGITS
    egd
    0.08
    ymar
    0.08
    ç¼ĸè¾ijäºİ
    0.08
    Ø·ÙģÙī
    0.07
    dob
    0.07
    åħ¢
    0.07
    ToEnd
    0.07
    -corner
    0.07
    beh
    0.07
    UDO
    0.07
    Activations Density 0.008%

    No Known Activations