© 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. 3871
    Prev
    Next
    INDEX
    Explanations

    inform someone

    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
    *scale
    -0.23
    abcdefghijklmnop
    -0.21
    aveled
    -0.21
    èĭŀ
    -0.21
    ABCDEFGHIJKLMNOP
    -0.21
    -provider
    -0.21
    /english
    -0.21
    :params
    -0.21
    izona
    -0.21
    atron
    -0.21
    POSITIVE LOGITS
     freely
    0.26
    çī½
    0.25
    èĩªçĶ±
    0.25
    çīµ
    0.23
    çŁ¥éģĵèĩªå·±
    0.23
    ä½Ļä¸ĩåħĥ
    0.21
    æĹłçŁ¥
    0.21
    è®°èĢħéĩĩ访
    0.20
    ewolf
    0.20
     loose
    0.20
    Activations Density 0.155%

    No Known Activations