© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3154
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æķ´ä¸ª
    -0.28
     entire
    -0.27
     area
    -0.23
     whole
    -0.23
     and
    -0.23
    1
    -0.23
    ime
    -0.22
     "
    -0.21
    ,
    -0.20
    :
    -0.20
    POSITIVE LOGITS
    âļĹ
    0.40
    ðŁĵIJ
    0.39
     newcom
    0.34
     Erectile
    0.33
     èĩªåĬ¨çĶŁæĪIJ
    0.30
    #aa
    0.29
    /OR
    0.29
     MessageBoxIcon
    0.28
    __;
    0.28
    #af
    0.27
    Activations Density 0.801%

    No Known Activations