© 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. 30856
    Prev
    Next
    INDEX
    Explanations

    mycodes/moniker/boost/operative/cv

    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
    pe
    -0.06
     (
    -0.06
     ...
    -0.06
     A
    -0.06
     ↵
    -0.06
     \"
    -0.05
    è¾±
    -0.05
    °
    -0.05
    yo
    -0.05
    ope
    -0.05
    POSITIVE LOGITS
    éĺµé£İ
    0.09
    ç¡ķ士çĶŁ
    0.09
    ucc
    0.09
    Äĵr
    0.08
    unis
    0.08
    sov
    0.08
    ervis
    0.08
    åŃ£åIJİ
    0.08
    åıĸæ¶Ī
    0.08
    uca
    0.08
    Activations Density 0.053%

    No Known Activations