© 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. 43343
    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
    aea
    -0.08
    REF
    -0.07
    itals
    -0.07
    anders
    -0.07
    _namespace
    -0.06
    Å¡a
    -0.06
    çħĻ
    -0.06
    xm
    -0.06
    转载请注æĺİ
    -0.06
    .ref
    -0.06
    POSITIVE LOGITS
    åĩ«
    0.07
    ært
    0.07
    luv
    0.07
    hirt
    0.07
    гаÑĤ
    0.07
    å°Ķå¾·
    0.07
    agli
    0.07
    ÑĤил
    0.07
    izzle
    0.07
     pseudo
    0.07
    Activations Density 0.000%

    No Known Activations