© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2493
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     incontri
    -0.31
     Clintons
    -0.29
     boobs
    -0.28
    /respond
    -0.27
     migliori
    -0.26
    /stretch
    -0.26
     adulti
    -0.25
    æ³ķå¸ĪèģĮä¸ļ
    -0.25
     helf
    -0.25
     CircularProgress
    -0.24
    POSITIVE LOGITS
     comunitÃł
    0.22
     CDDL
    0.21
    @qq
    0.21
    .MSG
    0.21
    -alist
    0.20
     muslim
    0.20
     ricerca
    0.20
    å¤©åºľ
    0.20
     coppia
    0.19
    èĥŃ
    0.19
    Activations Density 1.592%

    No Known Activations