© 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. 11747
    Prev
    Next
    INDEX
    Explanations

    plays in a class

    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
    ollar
    -0.09
    prus
    -0.08
    amak
    -0.07
    amaz
    -0.07
    thetic
    -0.07
    éĽģ
    -0.07
    olls
    -0.07
    quee
    -0.07
    indexed
    -0.07
    ilm
    -0.07
    POSITIVE LOGITS
     bram
    0.07
     rep
    0.07
    avier
    0.06
     tao
    0.06
    åĴĮéĥ¨åĪĨ
    0.06
    atest
    0.06
    Ñħай
    0.06
     torm
    0.06
     Algar
    0.06
    çoit
    0.06
    Activations Density 0.017%

    No Known Activations