© 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. 8678
    Prev
    Next
    INDEX
    Explanations

    hold up, wait a minute

    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
    enna
    -0.08
     verl
    -0.08
    çĦ¶æĺ¯
    -0.07
    大æĪIJ
    -0.07
    èį·
    -0.07
    osg
    -0.07
    èĩªè¡ĮæıIJä¾Ľ
    -0.07
    iles
    -0.07
    Hint
    -0.07
    Hints
    -0.07
    POSITIVE LOGITS
    isma
    0.08
    ä¹ĭå®Ŀ
    0.07
    جاÙħ
    0.07
    åıijçĶŁçļĦäºĭæĥħ
    0.06
    inson
    0.06
    ©
    0.06
    à¹ĥà¸Ļà¸Ħวาม
    0.06
    istrator
    0.06
    iak
    0.06
    éĩijçİī
    0.06
    Activations Density 0.004%

    No Known Activations