© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 169
    Prev
    Next
    INDEX
    Explanations

    citation references

    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
    	Copyright
    -0.22
    çĥ¬
    -0.19
    /fixtures
    -0.19
    niÄħ
    -0.18
    解说
    -0.18
    _corner
    -0.18
    (&:
    -0.18
    çĸ³
    -0.18
    æľīåĬ©
    -0.17
    åħĭèݱ
    -0.17
    POSITIVE LOGITS
     CircularProgress
    0.28
     scarc
    0.24
    naments
    0.23
    osemite
    0.23
    -Trump
    0.23
    ients
    0.23
    :";č↵
    0.22
    olls
    0.22
    orks
    0.22
    ".↵↵↵↵
    0.22
    Activations Density 0.085%

    No Known Activations