© 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. 48215
    Prev
    Next
    INDEX
    Explanations

    statement, definition, proposition, formulation

    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
    ahiran
    -0.08
    çª
    -0.07
    å§ĵ
    -0.07
    å¨Ĩ
    -0.07
     sót
    -0.07
    estern
    -0.07
    ä¸ĢçŃ¹
    -0.07
    awal
    -0.07
    æľ¬æĢ§
    -0.07
    á»įc
    -0.07
    POSITIVE LOGITS
    表述
    0.08
     version
    0.08
     definitions
    0.08
    éĻĪè¿°
    0.08
     formulation
    0.08
    å½¢å¼ı
    0.08
    æ¦Ĥæĭ¬
    0.08
     proposition
    0.08
     definition
    0.07
     propositions
    0.07
    Activations Density 0.028%

    No Known Activations