© 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. 45974
    Prev
    Next
    INDEX
    Explanations

    .plan @implementation

    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
    inni
    -0.08
     presumably
    -0.08
    èĩ³å°ij
    -0.08
    èµ·çłģ
    -0.07
    èĩ³å°ijæľī
    -0.07
     either
    -0.07
    urr
    -0.07
    usus
    -0.06
     EITHER
    -0.06
    è¦ģä¹Īæĺ¯
    -0.06
    POSITIVE LOGITS
    metrics
    0.09
    паÑģ
    0.07
    aroo
    0.07
    มูล
    0.07
     Avg
    0.07
    hdl
    0.07
    èĩªå·±åİ»
    0.07
    รุ
    0.07
    hdr
    0.07
     elaborate
    0.07
    Activations Density 0.007%

    No Known Activations