© 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. 51544
    Prev
    Next
    INDEX
    Explanations

    code snippets or citations

    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
    _ATOMIC
    -0.08
    æ²»
    -0.07
    平顶
    -0.07
    arder
    -0.07
    åĨ³èĥľ
    -0.07
    æĦıè¯Ĩ
    -0.07
    جÙħØ©
    -0.07
    ette
    -0.07
    erge
    -0.07
    gres
    -0.07
    POSITIVE LOGITS
    éģµå®ĪåĽ½å®¶
    0.07
    ÖĦ
    0.06
    å®ĥæīĢ
    0.06
    åıĪä¸įæĺ¯
    0.06
    Ù±
    0.06
    rap
    0.06
    æľªå®Įå¾ħç»Ń
    0.06
    çļĦä¸įæĺ¯
    0.06
    Ú©ÙĦ
    0.06
    åį´å¾Ī
    0.06
    Activations Density 0.002%

    No Known Activations