© 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. 13118
    Prev
    Next
    INDEX
    Explanations

    direction and position

    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
    ä¼½
    -0.07
    trice
    -0.07
    ellit
    -0.07
    ENCED
    -0.07
     crom
    -0.07
    åĴĮä¸ī
    -0.07
     fác
    -0.06
     Ejem
    -0.06
    esito
    -0.06
     óp
    -0.06
    POSITIVE LOGITS
    uhn
    0.08
    ëĵ¯
    0.07
    è¶Ĭéķ¿
    0.07
    为å®ĹæŨ
    0.07
    oven
    0.07
    adou
    0.07
    就让
    0.07
    åĪĻ认为
    0.07
    vers
    0.06
    à¹Ģà¸Ľà¹ĩà¸Ļหลัà¸ģ
    0.06
    Activations Density 0.001%

    No Known Activations