© 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. 2937
    Prev
    Next
    INDEX
    Explanations

    crime and legal actions

    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
    oneksi
    -0.23
    ++;č↵č↵
    -0.23
    #ad
    -0.21
    ometown
    -0.20
     Ä°stanbul
    -0.20
    PMENT
    -0.20
    ëIJĺ기
    -0.20
    crast
    -0.20
    */,↵
    -0.19
    rets
    -0.19
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.21
     reportedly
    0.21
    é¼¾
    0.20
     avaliações
    0.20
    :checked
    0.20
    缸åħ³éĥ¨éŨ
    0.19
    åĪĿæŃ¥
    0.19
    å«Į
    0.19
    boards
    0.19
    arent
    0.19
    Activations Density 0.586%

    No Known Activations