© 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. 43007
    Prev
    Next
    INDEX
    Explanations

    punctuation following code

    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
     Frat
    -0.07
    alj
    -0.07
    >>)
    -0.07
    )':
    -0.07
    }')
    -0.07
    })(
    -0.07
    abt
    -0.07
    اتÙĬ
    -0.06
    >}
    -0.06
    ningar
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.10
    åľ°å®ĮæĪIJ
    0.08
    å¸ĮæľĽåı¯ä»¥
    0.07
    à¦Ĥ
    0.07
    å¤Ħåľ¨
    0.07
    áĢ²áĢ·
    0.07
    ä¸ĥ大
    0.07
    <|box_end|>
    0.07
    èĢĮå¤į
    0.07
    çİ¥
    0.07
    Activations Density 0.400%

    No Known Activations