© 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. 50866
    Prev
    Next
    INDEX
    Explanations

    adding, increasing, disturbing, failure, exposure

    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
    tep
    -0.07
    ,),
    -0.06
    ]],
    -0.06
    (&$
    -0.06
     whence
    -0.06
    ++.
    -0.06
     />,
    -0.06
    éĤ£ä¹ĪçļĦ
    -0.06
    éĤ£ä½ł
    -0.06
     ],
    -0.06
    POSITIVE LOGITS
     ìľĦíķ´ìĦľëĬĶ
    0.10
    çļĦä¸ĢåĪĩéĥ½
    0.10
     ìĤ¬ìļ©íķĺë©´
    0.10
    å·¥ä½ľéľĢè¦ģ
    0.10
    à¸Ļีà¹īà¸Īะ
    0.10
     voilÃł
    0.09
    çłĶ究表æĺİ
    0.09
     infatti
    0.09
    æĢ§æĺ¯
    0.09
    ç»ĵæŀľè¡¨æĺİ
    0.09
    Activations Density 0.282%

    No Known Activations