© 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. 27392
    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
    åIJİè¿Ľ
    -0.07
    rebs
    -0.07
    ra
    -0.07
    äºĭå®ľ
    -0.06
    ohl
    -0.06
    veen
    -0.06
    ä¸ĭåĪĹéĹ®é¢ĺ
    -0.06
    SCRIPT
    -0.06
    è¾ŀæŧ
    -0.06
     Stud
    -0.06
    POSITIVE LOGITS
    uny
    0.08
    Occurrences
    0.08
    uments
    0.08
    大路
    0.08
    umento
    0.08
    antung
    0.07
    &S
    0.07
    ommy
    0.07
    egrity
    0.07
    áĥ
    0.07
    Activations Density 0.000%

    No Known Activations