© 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. 1036
    Prev
    Next
    INDEX
    Explanations

    negative connotations, misuse, abused

    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
    intang
    -0.07
    éŁ¿
    -0.07
    éįµ
    -0.06
    avais
    -0.06
    Prob
    -0.06
     shocked
    -0.06
    æŃ£å¸¸äºº
    -0.06
    ets
    -0.06
    ©
    -0.06
    èĬ¬èĬ³
    -0.06
    POSITIVE LOGITS
     neglect
    0.10
    沦为
    0.09
     misuse
    0.09
    滥çĶ¨
    0.09
     overly
    0.09
    è¿ĩ度
    0.08
    è¿ĩäºİ
    0.08
    å½¢å¼ı主ä¹ī
    0.08
     né
    0.08
     ì§ĢëĤĺ
    0.08
    Activations Density 0.086%

    No Known Activations