© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22869
    Prev
    Next
    INDEX
    Explanations

    lua.h

    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
    éĻIJ
    -0.07
     Smy
    -0.07
    åħ¸
    -0.06
    ferred
    -0.06
    aison
    -0.06
    uali
    -0.06
    æ¸ħäºĨ
    -0.06
    å¸ĪèĮĥåѦéĻ¢
    -0.06
    ilm
    -0.06
     submar
    -0.06
    POSITIVE LOGITS
    éĢĤå½ĵåľ°
    0.09
    uhu
    0.08
    unti
    0.08
    éĽĢ
    0.07
    çĥģ
    0.07
    HING
    0.07
     Tend
    0.07
    emo
    0.07
    èĩªå·±çļĦåĬªåĬĽ
    0.07
    ortable
    0.07
    Activations Density 0.048%

    No Known Activations