© 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. 49558
    Prev
    Next
    INDEX
    Explanations

    will relate or have discussed

    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
    of
    -0.07
     Yay
    -0.07
    /
    -0.06
    æĺ¯åIJĹ
    -0.06
    èĭĩ
    -0.06
    ä½ľ
    -0.06
    纲
    -0.06
    å»ºè®¾æľŁ
    -0.06
    _DYNAMIC
    -0.06
    ergestellt
    -0.06
    POSITIVE LOGITS
    ETTA
    0.07
    对äºİéĤ£äºĽ
    0.07
    )':
    0.07
    quera
    0.07
    åĮĪ
    0.07
    èĭ¦è¾£
    0.07
     noti
    0.07
    oso
    0.07
    }//
    0.07
    åħ³äºİåģļ好
    0.07
    Activations Density 0.009%

    No Known Activations