© 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. 62353
    Prev
    Next
    INDEX
    Explanations

    fascist nationalism, Becker muscular, curly hair, turn right

    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
    reja
    -0.08
     misk
    -0.08
    ABIL
    -0.08
    åľ¨å¿ħ
    -0.08
     inilah
    -0.08
    ÙĥÙĦÙĬ
    -0.08
    éģĵæĿ¥
    -0.08
    öre
    -0.08
    ä½ıè¡Į
    -0.08
    ibun
    -0.08
    POSITIVE LOGITS
    åıįä¹ĭ
    0.07
     or
    0.06
     worthy
    0.06
    è¦ģä¹Īæĺ¯
    0.06
    æĪĸ
    0.06
    beck
    0.06
    hent
    0.06
    ++;
    0.06
     disguised
    0.06
    anian
    0.05
    Activations Density 0.011%

    No Known Activations