© 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. 47082
    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
    -0.07
    aka
    -0.06
    ç¿»
    -0.06
     chil
    -0.06
     fat
    -0.06
     prep
    -0.06
    ä¸ĢçĤ¹
    -0.06
    era
    -0.06
     Osw
    -0.06
    çªģ
    -0.06
    POSITIVE LOGITS
    iclet
    0.09
    _CONT
    0.09
     trecho
    0.08
    trail
    0.08
    asilan
    0.08
    udir
    0.08
    è¡Įä¹ĭ
    0.08
    ynet
    0.08
    .PARAM
    0.08
    åĨįä¸Ĭæĸ°åı°éĺ¶
    0.08
    Activations Density 0.000%

    No Known Activations