© 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. 34100
    Prev
    Next
    INDEX
    Explanations

    other times

    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
    icer
    -0.07
    /opt
    -0.07
    smith
    -0.07
    ehr
    -0.06
    ä»İåīį
    -0.06
    æĺ¯çĶ¨
    -0.06
    ucht
    -0.06
    ä»İå·¦
    -0.06
    สัà¸ķ
    -0.06
    æ¯ıåı°
    -0.06
    POSITIVE LOGITS
    alti
    0.08
    onis
    0.08
     PARTY
    0.07
     mest
    0.07
    adam
    0.07
     untouched
    0.07
    å·´åĭĴ
    0.07
    Õ®
    0.07
    ase
    0.07
    fds
    0.07
    Activations Density 0.018%

    No Known Activations