© 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. 42161
    Prev
    Next
    INDEX
    Explanations

    side, death, behind, through, above, behaviour, ward

    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
    лек
    -0.07
    ilton
    -0.07
    ?-
    -0.07
    åĩºæĿ¥
    -0.07
    orary
    -0.07
    endt
    -0.07
    |string
    -0.07
    å«ĮçĬ¯
    -0.07
    оÑĢий
    -0.06
    è½®çķª
    -0.06
    POSITIVE LOGITS
    -comments
    0.07
    çĶ¸
    0.07
    zens
    0.07
    æľī礼
    0.06
    人æĦı
    0.06
    gehend
    0.06
    åħ¶éģĵ
    0.06
    elj
    0.06
    å°ļ
    0.06
    eps
    0.06
    Activations Density 0.001%

    No Known Activations