© 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. 12630
    Prev
    Next
    INDEX
    Explanations

    seekers of money or raises

    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
    yan
    -0.06
    itera
    -0.06
    деÑĤÑģÑı
    -0.06
    å®ĮæĪIJæĬķèµĦ
    -0.06
    ä¸ĭæĶ¾
    -0.06
    belast
    -0.06
    andel
    -0.06
     تÙĤرÙĬب
    -0.06
    åŃ¦ä¹łåĪ°
    -0.06
    olik
    -0.06
    POSITIVE LOGITS
    æľªæŀľ
    0.14
    สัà¸ģ
    0.09
    çļĦæ¬²æľĽ
    0.08
    ç»Īäºİåľ¨
    0.08
    ä¸İå®ŀéĻħ
    0.08
    çļĦå¿ĥæĢģ
    0.08
    å®ģæĦ¿
    0.08
    ä½Ĩå®ŀéĻħä¸Ĭ
    0.08
    izen
    0.08
    è¿Łè¿Ł
    0.08
    Activations Density 0.254%

    No Known Activations