© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 13207
    Prev
    Next
    INDEX
    Explanations

    newbie or beginner

    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
    à¸ģà¹ĩà¹Ħà¸Ķà¹ī
    -0.08
    ("");
    -0.08
     '';
    -0.08
    ().
    -0.07
    ("").
    -0.07
     ;
    -0.07
    '];
    -0.07
    à¹Ħà¸Ķà¹īà¹Ģลย
    -0.07
    ('').
    -0.07
    ï¼Ľ
    -0.07
    POSITIVE LOGITS
     _______,
    0.12
    ,it
    0.11
    ,this
    0.10
    çļĦç¼ĺæķħ
    0.10
    ,is
    0.10
     Ù쨥ÙĨ
    0.10
     '_',
    0.10
    ç¼ĺæķħ
    0.09
    .*,
    0.09
     inilah
    0.09
    Activations Density 0.152%

    No Known Activations