© 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. 19884
    Prev
    Next
    INDEX
    Explanations

    artifactual interpretation

    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
    ilde
    -0.08
    æ¶ī
    -0.07
    ãĥģãĥ©
    -0.07
     tast
    -0.07
     bran
    -0.07
    .ent
    -0.07
    å¯Ĩå¯Ĩ
    -0.06
    ä»·
    -0.06
     اÙħÙĪر
    -0.06
    ytt
    -0.06
    POSITIVE LOGITS
     falsely
    0.13
     artificially
    0.10
     false
    0.10
     palsu
    0.10
    false
    0.09
     incorrectly
    0.09
     unfairly
    0.09
    ä¸įå¿ħè¦ģçļĦ
    0.08
     unrelated
    0.08
     prematurely
    0.08
    Activations Density 0.035%

    No Known Activations