© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2985
    Prev
    Next
    INDEX
    Explanations

    return statements

    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
    åħ¨ç¨ĭ
    -0.08
    æľīæĥħ
    -0.08
    мии
    -0.08
    łĢ
    -0.07
    梯éĺŁ
    -0.07
    äºĭä¸Ń
    -0.07
    æľī以ä¸ĭ
    -0.07
    åĭĩå¾Ģ缴åīį
    -0.07
    å¦Ĥ鼨
    -0.07
    å¼Ģèĥĥ
    -0.07
    POSITIVE LOGITS
     return
    0.08
    return
    0.07
     returning
    0.07
     Return
    0.07
    Return
    0.07
    éģ£
    0.07
    -return
    0.07
    enni
    0.06
    throw
    0.06
    Throw
    0.06
    Activations Density 0.029%

    No Known Activations