© 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. 15591
    Prev
    Next
    INDEX
    Explanations

    unrelated or irrelevant concepts

    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
     sahib
    -0.07
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    -0.07
    áh
    -0.07
    çĥĻ
    -0.07
     abus
    -0.07
    .op
    -0.07
    áºŃn
    -0.07
    FieldName
    -0.07
    åĨįä¸į
    -0.07
     Former
    -0.07
    POSITIVE LOGITS
     unrelated
    0.10
    æĹłåħ³
    0.09
    æľªå¿ħ
    0.08
     irrelevant
    0.08
     ë³Ħë¡ľ
    0.08
    auc
    0.08
    并没æľī
    0.08
    并æĹł
    0.08
    ä¸įä¸Ģå®ļ
    0.08
    并ä¸įä¼ļ
    0.08
    Activations Density 0.004%

    No Known Activations