© 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. 1632
    Prev
    Next
    INDEX
    Explanations

    unaffected by conditions

    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
    ä½Ĩ没æľī
    -0.08
    veille
    -0.08
    õi
    -0.08
    arz
    -0.08
    æĶ¶çĽĺ
    -0.08
    Targets
    -0.07
    çIJĽ
    -0.07
     meiden
    -0.07
    otta
    -0.07
    纳æĸ¯
    -0.07
    POSITIVE LOGITS
    åıªè¦ģ
    0.11
    ä¸įå½±åĵį
    0.11
     unaffected
    0.11
    ä¸įåıĺ
    0.10
     except
    0.10
    åıªè¦ģä½ł
    0.09
    åı¯ä»¥æĶ¾å¿ĥ
    0.09
    except
    0.09
    éĻ¤éĿŀ
    0.09
    å¤īãĤıãĤīãģªãģĦ
    0.09
    Activations Density 0.056%

    No Known Activations