© 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. 43690
    Prev
    Next
    INDEX
    Explanations

    geographical categories

    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
    vecs
    -0.07
    Queryable
    -0.07
    踵
    -0.07
     (*
    -0.07
    ловиÑĩ
    -0.06
    TypeId
    -0.06
    å°½æĺ¯
    -0.06
    ousel
    -0.06
    _ERRORS
    -0.06
    éĩijåŃIJ
    -0.06
    POSITIVE LOGITS
    &
    0.13
    æļ¨
    0.11
    -and
    0.11
    åħ¼
    0.11
    _and
    0.11
    /
    0.10
     &
    0.10
    &D
    0.09
    &C
    0.09
    _AND
    0.09
    Activations Density 0.422%

    No Known Activations