© 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. 3167
    Prev
    Next
    INDEX
    Explanations

    list items

    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
    /inet
    -0.23
    ocop
    -0.21
     Attr
    -0.19
    SqlParameter
    -0.19
    bservable
    -0.19
    isoner
    -0.19
    inceton
    -0.18
    ìłľ
    -0.18
    .sections
    -0.18
    æľ½
    -0.18
    POSITIVE LOGITS
    .ToShort
    0.22
    .camel
    0.20
     Cath
    0.18
    ux
    0.18
    opez
    0.18
    åĵªå®¶å¥½
    0.18
    åĿļ
    0.18
    Nguá»ĵn
    0.17
    æĹİ
    0.17
    @Setter
    0.17
    Activations Density 0.001%

    No Known Activations