© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2419
    Prev
    Next
    INDEX
    Explanations

    URL encoding and shortened text

    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
    lei
    -0.09
    á»İ
    -0.08
    ä¸į欲
    -0.08
    åı¯æľĽ
    -0.08
    नà¥ģ
    -0.07
    तà¥įरà¥Ģ
    -0.07
    lek
    -0.07
    è¨Ģä¹ĭ
    -0.07
    etti
    -0.07
    nty
    -0.07
    POSITIVE LOGITS
    uellement
    0.07
    ovie
    0.07
    el
    0.06
    çĤ¹çģ«
    0.06
    _dirty
    0.06
    大年åĪĿ
    0.06
    ience
    0.06
    гам
    0.06
    иÑĩ
    0.06
    åįĥéĩĮ
    0.06
    Activations Density 0.037%

    No Known Activations