© 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. 56487
    Prev
    Next
    INDEX
    Explanations

    Evening of Dreams, superFIT, viscolin, Green bundles, personal neglect, linear connectors, Great Osage Trail, silicon disks

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    elop
    -0.07
    egov
    -0.07
    _ASSOC
    -0.06
    æĤł
    -0.06
    odat
    -0.06
    ampe
    -0.06
    Ñĩком
    -0.06
    æĨij
    -0.06
    endas
    -0.06
    dings
    -0.06
    POSITIVE LOGITS
    ç½ijåıĭè¯Ħ论
    0.07
    è·¯éĢı
    0.07
     aforementioned
    0.07
    мба
    0.07
    è¨Ģæĥħå°ı说
    0.06
     genannte
    0.06
    çŃīæĸ°
    0.06
    orget
    0.06
    æµ®çĶŁ
    0.06
    <|box_end|>
    0.06
    Activations Density 0.266%

    No Known Activations