© 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. 58236
    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
    terer
    -0.09
    è½°è½°
    -0.09
    dere
    -0.08
    ahi
    -0.08
    λλα
    -0.08
    klet
    -0.07
    revet
    -0.07
     Lec
    -0.07
    kel
    -0.07
    aka
    -0.07
    POSITIVE LOGITS
    澡
    0.07
    æĪĺæĸĹ
    0.07
     continuation
    0.06
    halb
    0.06
     Booker
    0.06
     pein
    0.06
     Ùħب
    0.06
    ût
    0.06
     implicit
    0.06
    umul
    0.06
    Activations Density 0.000%

    No Known Activations