© 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. 58291
    Prev
    Next
    INDEX
    Explanations

    autobiographer - limited - string

    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
    rup
    -0.09
     RESERVED
    -0.08
    /weather
    -0.08
    raub
    -0.08
    iento
    -0.08
    -ves
    -0.08
    ç¦ģæŃ¢è½¬è½½
    -0.07
    íĮ
    -0.07
    çħĮ
    -0.07
    -/
    -0.07
    POSITIVE LOGITS
    kej
    0.07
    å¿ħè¦ģ
    0.06
    ï¼Ī
    0.06
     dijal
    0.06
    ä¸įè¯Ĩ
    0.06
    ÄĽj
    0.06
    è¯Ĩ
    0.06
    iltr
    0.06
    ovnÃŃ
    0.06
    ç¿°
    0.06
    Activations Density 0.012%

    No Known Activations