© 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. 22930
    Prev
    Next
    INDEX
    Explanations

    assignment `r`

    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
    ][:
    -0.07
    å¸ĮæľĽå¤§å®¶èĥ½å¤Ł
    -0.07
    è·¯ä¸İ
    -0.07
    áp
    -0.07
    }:
    -0.07
    <[
    -0.07
    rific
    -0.07
    ization
    -0.07
    pios
    -0.07
    vvm
    -0.06
    POSITIVE LOGITS
     ,,
    0.09
    åĴ
    0.07
     ‘’
    0.07
    èĩªå·²
    0.07
    ãĢģãĢģ
    0.07
    è¿Ħ
    0.06
    ãģ¶
    0.06
    ê°ĦìĹIJ
    0.06
    à±Ĩ
    0.06
    fty
    0.06
    Activations Density 0.464%

    No Known Activations