© 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. 40520
    Prev
    Next
    INDEX
    Explanations

    chemical elements

    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
    ML
    -0.07
    utc
    -0.07
    åı£éķĩ
    -0.06
    ime
    -0.06
    utta
    -0.06
    æ¡£
    -0.06
    æī¾
    -0.06
    ÃŃsimo
    -0.06
    ig
    -0.06
    -
    -0.06
    POSITIVE LOGITS
    instein
    0.09
     Istri
    0.09
    enticator
    0.09
    essant
    0.08
    üste
    0.08
    Ä©
    0.08
    apkan
    0.08
    å®Īä¿¡
    0.08
    orden
    0.08
    chsel
    0.08
    Activations Density 0.019%

    No Known Activations