© 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. 20150
    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
    TEGR
    -0.08
    dade
    -0.08
    è¾¾åĨħ
    -0.08
    estro
    -0.08
    .way
    -0.08
    ×ķ×ķת
    -0.07
    illo
    -0.07
    orna
    -0.07
    ris
    -0.07
    æĽľ
    -0.07
    POSITIVE LOGITS
    ully
    0.06
     nanti
    0.06
     Miguel
    0.06
     Fuji
    0.06
     based
    0.06
    0.06
    tram
    0.06
    igent
    0.05
    RET
    0.05
    èĩªå·±åģļ
    0.05
    Activations Density 0.000%

    No Known Activations