© 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. 2415
    Prev
    Next
    INDEX
    Explanations

    S

    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
    %;"
    -0.23
    InputElement
    -0.21
     Bakan
    -0.20
    @testable
    -0.19
    诺
    -0.19
    å°´
    -0.19
    InputChange
    -0.19
     Strateg
    -0.19
    /Typography
    -0.18
    åįļ
    -0.18
    POSITIVE LOGITS
     UsersController
    0.20
    çĸł
    0.20
    åĬ¬
    0.20
    èµĢ
    0.19
     }):
    0.19
    GIN
    0.18
    ÙģÙĤ
    0.18
    anela
    0.18
     EXPRESS
    0.18
     Advertisement
    0.18
    Activations Density 0.009%

    No Known Activations