© 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. 28666
    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
    éĵ¶å±±
    -0.08
    ocker
    -0.08
     EDUCA
    -0.07
    orgt
    -0.07
    rine
    -0.07
    Ĵ·
    -0.07
    स
    -0.07
    äch
    -0.07
    nicos
    -0.07
    èįĶ
    -0.07
    POSITIVE LOGITS
    æĺ¯ç»ı
    0.07
    'er
    0.06
     abstract
    0.06
     sap
    0.06
     ter
    0.06
     Ter
    0.06
    TERM
    0.06
    Ñijм
    0.06
    Opts
    0.06
    abung
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.