© 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. 448
    Prev
    Next
    INDEX
    Explanations

    adult content

    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
     pestic
    -0.33
    éĵij
    -0.30
     appré
    -0.29
    .IsNullOr
    -0.28
    .EventQueue
    -0.28
     licensors
    -0.27
    istrate
    -0.27
     MILF
    -0.27
     {?}
    -0.26
    .Fat
    -0.26
    POSITIVE LOGITS
    íĶĦë¡ľê·¸
    0.32
     Retorna
    0.31
    -redux
    0.29
     girlfriends
    0.28
     enthus
    0.28
    éĢ¶
    0.27
    çĬĦ
    0.27
    -vars
    0.27
     Leer
    0.27
     masturbating
    0.26
    Activations Density 18.209%

    No Known Activations