© 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. 13777
    Prev
    Next
    INDEX
    Explanations

    pulling or having pulled

    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
    ï¸ı
    -0.09
    uality
    -0.09
    ually
    -0.08
    éłĥ
    -0.08
    ilton
    -0.08
    ลฯ
    -0.08
    rawdÄĻ
    -0.08
    heu
    -0.07
    iring
    -0.07
    à¸ģารà¸ĵà¹Į
    -0.07
    POSITIVE LOGITS
    æĭ½
    0.11
    er
    0.11
    -away
    0.08
    erait
    0.08
     consigo
    0.08
    ÑģÑĤÑı
    0.08
    éķ¿è¡¥çŁŃ
    0.08
    ington
    0.08
    åĭĴæĸ¯
    0.07
     balik
    0.07
    Activations Density 0.025%

    No Known Activations