© 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. 2898
    Prev
    Next
    INDEX
    Explanations

    to

    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
    å¥¥åľ°
    -0.23
    ERTICAL
    -0.23
    IRTUAL
    -0.21
    =\"/
    -0.21
    æĴĻ
    -0.20
    {@
    -0.20
    *)"
    -0.20
    ⾬
    -0.20
    %%%%%%%%%%%%%%%%
    -0.20
    hibited
    -0.19
    POSITIVE LOGITS
     scrutiny
    0.28
     influences
    0.27
     whims
    0.24
     attack
    0.24
    çĸ«æĥħå½±åĵį
    0.23
     influence
    0.22
    çļĦå½±åĵį
    0.21
     Influ
    0.21
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.20
     gaze
    0.20
    Activations Density 0.334%

    No Known Activations