© 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. 2782
    Prev
    Next
    INDEX
    Explanations

    timestamps

    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
    髯
    -0.20
    }elseif
    -0.20
    妪
    -0.20
    loquent
    -0.20
    媵
    -0.20
    são
    -0.20
    .Gray
    -0.19
    -Apr
    -0.19
    opolitan
    -0.19
    bote
    -0.19
    POSITIVE LOGITS
    女æĺŁ
    0.21
    æ¯Ķäºļ
    0.20
    creds
    0.20
    GLuint
    0.19
    aken
    0.19
    ожеÑĤ
    0.19
    èİĵ
    0.18
    vably
    0.18
    ]={↵
    0.18
     Purs
    0.18
    Activations Density 0.006%

    No Known Activations