© 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. 12941
    Prev
    Next
    INDEX
    Explanations

    asking for or explaining proofs

    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
    çĽ¸å¯¹çļĦ
    -0.08
    åıªæ±Ĥ
    -0.08
    -encoded
    -0.07
    ÑĢеа
    -0.07
     predicts
    -0.07
    Encoded
    -0.07
    çķ¸
    -0.07
     eingestellt
    -0.07
    åıªä»£è¡¨
    -0.07
    è¿Ľè¡ĮåĴ¨è¯¢
    -0.07
    POSITIVE LOGITS
    çļĦè¯ģæĺİ
    0.13
    è¯ģæĺİ
    0.13
     proofs
    0.12
     proof
    0.11
     proving
    0.10
     доказаÑĤелÑĮÑģÑĤва
    0.10
    论è¯ģ
    0.10
     доказ
    0.10
    Proof
    0.09
     Proof
    0.09
    Activations Density 0.060%

    No Known Activations