© 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. 32253
    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
    iki
    -0.08
    ÑĮем
    -0.07
    #!
    -0.07
    izzi
    -0.07
    води
    -0.07
    olec
    -0.07
    //@
    -0.07
    ئ
    -0.07
    æľĢç®ĢåįķçļĦ
    -0.07
    éĢĤå½ĵåľ°
    -0.07
    POSITIVE LOGITS
    fav
    0.07
    iaux
    0.07
    upal
    0.07
     hẳn
    0.07
    isant
    0.07
    /rules
    0.06
     Hv
    0.06
     fav
    0.06
    éĢīåŀĭ
    0.06
    éĢīè°ĥ
    0.06
    Activations Density 0.000%

    No Known Activations