© 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. 7913
    Prev
    Next
    INDEX
    Explanations

    choke, thrust, pressure, fucking

    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
    èĩªæķij
    -0.08
    èĩªæĪijä¿ĿæĬ¤
    -0.07
    æīĵæĸĹ
    -0.07
    ä½ĨæĦ¿
    -0.07
    lest
    -0.07
     protective
    -0.06
    æĬµå¾¡
    -0.06
     Shields
    -0.06
    å®ıè§Ĥ
    -0.06
    æĬĹäºī
    -0.06
    POSITIVE LOGITS
    éĢ¼
    0.10
     exploit
    0.09
    迫使
    0.09
    æŃ¥æŃ¥
    0.09
     exploiting
    0.09
    追åĩ»
    0.09
    ä¸Ģæ°Ĺãģ«
    0.08
     irresistible
    0.08
    ä¹ĭåĬ¿
    0.08
    ://%
    0.08
    Activations Density 0.039%

    No Known Activations