© 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. 47058
    Prev
    Next
    INDEX
    Explanations

    comments after slash

    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
    æĥħ人
    -0.08
    ebet
    -0.08
    æŁĶ软çļĦ
    -0.07
    μία
    -0.07
    ãĥĹãĥĪ
    -0.07
     zakÅĤad
    -0.07
    endir
    -0.07
    å¦Ĥå±±
    -0.07
    大åĪĢ
    -0.07
     netr
    -0.07
    POSITIVE LOGITS
     Tide
    0.07
    åºļ
    0.07
    éĢłçº¸
    0.06
     joh
    0.06
    surf
    0.06
     poli
    0.06
    agli
    0.06
     Polit
    0.06
     Sti
    0.06
    Ãłng
    0.06
    Activations Density 0.045%

    No Known Activations