© 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. 30533
    Prev
    Next
    INDEX
    Explanations

    toggled or cut out

    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
    catch
    -0.08
    çļĦä¿Ŀè¯ģ
    -0.07
    .Safe
    -0.07
     Catch
    -0.07
    Catch
    -0.07
     Slut
    -0.07
    ¬¸
    -0.07
     Fet
    -0.07
     catch
    -0.06
    abet
    -0.06
    POSITIVE LOGITS
     togg
    0.08
    äºĮè¿ĽåĪ¶
    0.08
    ç¨Ģçĸı
    0.08
    laut
    0.08
    æ¿Ģæ´»
    0.07
    sparse
    0.07
    åĩºå¥ĩ
    0.07
    å¸ĥå°Ķ
    0.07
    sel
    0.07
     Boolean
    0.07
    Activations Density 0.038%

    No Known Activations