© 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. 25647
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    rau
    -0.07
    ìĪĺë¡Ŀ
    -0.07
     Vegas
    -0.06
    eley
    -0.06
    lein
    -0.06
     liken
    -0.06
     Seek
    -0.06
    Seite
    -0.06
    пил
    -0.06
     Einz
    -0.06
    POSITIVE LOGITS
    .bind
    0.09
    ç»ij
    0.08
    '](
    0.08
    adah
    0.08
    ojis
    0.08
    /bind
    0.08
    meen
    0.07
    eci
    0.07
    ciano
    0.07
    带大家
    0.07
    Activations Density 0.000%

    No Known Activations