© 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. 28840
    Prev
    Next
    INDEX
    Explanations

    equipment, overview, suggested, substances

    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
    åį´å§ĭç»Ī
    -0.08
    óst
    -0.08
    iores
    -0.08
    ukai
    -0.08
    rios
    -0.08
    ÙĬارة
    -0.08
    æķ¬è¯·æľŁå¾ħ
    -0.08
    _ARGUMENT
    -0.08
    é¡»åľ¨
    -0.07
     Journ
    -0.07
    POSITIVE LOGITS
    åı¯èĥ½æĺ¯
    0.06
    票
    0.06
    åı¯èĥ½
    0.06
    ãĤĭãģĵãģ¨ãģĮãģ§ãģįãģ¾ãģĻ
    0.06
    æĺ¯ä¸įæĺ¯
    0.06
     edin
    0.05
    大约
    0.05
    åħ¶ä»ĸ
    0.05
     aks
    0.05
    å¿ĹæĪIJ
    0.05
    Activations Density 0.006%

    No Known Activations