© 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. 947
    Prev
    Next
    INDEX
    Explanations

    than

    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
    2
    -0.34
    3
    -0.34
    0
    -0.32
    1
    -0.32
    5
    -0.32
    4
    -0.31
    9
    -0.31
    -
    -0.30
    8
    -0.30
    6
    -0.30
    POSITIVE LOGITS
    âļĹ
    0.39
    [".
    0.37
    ðŁĵIJ
    0.34
    Hôtel
    0.33
    __$
    0.32
    ï¼Ħ
    0.32
     +=↵
    0.31
    ournaments
    0.31
    gnore
    0.30
    /↵↵↵↵
    0.30
    Activations Density 0.602%

    No Known Activations