© 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. 40051
    Prev
    Next
    INDEX
    Explanations

    probabilistic calculations

    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
     Likewise
    -0.07
    mana
    -0.07
    immy
    -0.06
    omar
    -0.06
    éľĢè¦ģ使çĶ¨
    -0.06
    ç¦ģ
    -0.06
    åĽłä¸ºè¿ĻäºĽ
    -0.06
    åĽłä¸ºè¿Ļ个
    -0.06
    usc
    -0.06
    éľĢè¦ģè¿Ľè¡Į
    -0.06
    POSITIVE LOGITS
    ä»»ä½ķæŶåĢĻ
    0.09
    å¦Ĥæŀľä¸Ģ个
    0.09
    wes
    0.08
    çļĦä»»ä½ķ
    0.08
    chia
    0.08
    åľ¨ä»»ä½ķ
    0.07
    ä»»ä½ķéĹ®é¢ĺ
    0.07
    ä»»ä½ķä¸Ģ个
    0.07
    å¦Ĥæŀľåľ¨
    0.07
    èĢĮå·²
    0.07
    Activations Density 0.003%

    No Known Activations