© 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. 2853
    Prev
    Next
    INDEX
    Explanations

    field constraints

    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
    åħ«å¤§ä»¥æĿ¥
    -0.21
     safeg
    -0.21
    åľºåIJĪ
    -0.21
    ittel
    -0.20
    =-=-
    -0.20
    æĪķ
    -0.20
    ἡ
    -0.19
     *)((
    -0.19
     YYS
    -0.19
     /************************************************************************
    -0.19
    POSITIVE LOGITS
    å¿ħ
    0.29
     optional
    0.28
     nullable
    0.27
    required
    0.26
     required
    0.25
     default
    0.24
    nullable
    0.23
    éĽģ
    0.23
    optional
    0.23
    \Mapping
    0.22
    Activations Density 0.086%

    No Known Activations