© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23136
    Prev
    Next
    INDEX
    Explanations

    code syntax, URL components

    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
    æ¦Ķ
    -0.06
    sey
    -0.06
    -
    -0.06
    emann
    -0.06
    声èī²
    -0.06
    ãģ¾ãģĹãģ¦
    -0.06
    izarre
    -0.06
    elle
    -0.06
    sem
    -0.06
    '
    -0.06
    POSITIVE LOGITS
    gehend
    0.09
    å°ı家
    0.09
    ibert
    0.09
    iglie
    0.09
    ertes
    0.09
    ilig
    0.09
    ernels
    0.08
     prép
    0.08
    ANTED
    0.08
    impat
    0.08
    Activations Density 0.026%

    No Known Activations