© 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. 16330
    Prev
    Next
    INDEX
    Explanations

    predictions and expectations

    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
    hil
    -0.07
    nale
    -0.07
    æŀĦæĪIJçĬ¯ç½ªçļĦ
    -0.06
    æĺ¼å¤ľ
    -0.06
    æ¾Ħ
    -0.06
    occa
    -0.06
    reb
    -0.06
    onger
    -0.06
    -chevron
    -0.06
    æľĢè¿ij
    -0.06
    POSITIVE LOGITS
     promised
    0.14
    åİŁå®ļ
    0.14
    é¢ĦæľŁçļĦ
    0.13
    å½ĵåĪĿ
    0.13
    çķ¶åĪĿ
    0.13
    åĪĿè¡·
    0.13
     expectations
    0.13
    é¢ĦæĸĻ
    0.12
    expect
    0.12
     expected
    0.12
    Activations Density 0.384%

    No Known Activations