© 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. 56550
    Prev
    Next
    INDEX
    Explanations

    making a choice

    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
    εια
    -0.09
    å°¼äºļ
    -0.09
    schen
    -0.08
    ness
    -0.08
    çĶŁäº§æĢ»åĢ¼
    -0.08
    æ»Ķ
    -0.08
    melden
    -0.08
    á»ĵng
    -0.08
    подоб
    -0.07
    ized
    -0.07
    POSITIVE LOGITS
    lessly
    0.10
    fully
    0.09
    fulness
    0.09
    åħ³å¤´
    0.08
     raya
    0.08
    گاÙĩ
    0.08
    lessness
    0.08
    ä½Ļåľ°
    0.08
    ably
    0.07
    pard
    0.07
    Activations Density 0.015%

    No Known Activations