© 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. 2972
    Prev
    Next
    INDEX
    Explanations

    list separators

    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
    вÑĪие
    -0.24
    Tambah
    -0.24
     (
    -0.24
    å¦Ĥä¸ĭ
    -0.24
    ä¸ĭåĪĹ
    -0.22
    immel
    -0.21
    :<?
    -0.20
    ToRemove
    -0.20
     following
    -0.20
     Example
    -0.19
    POSITIVE LOGITS
    :
    0.55
    ï¼ļ
    0.45
     namely
    0.34
    _:
    0.33
    *:
    0.29
     _:
    0.28
     :
    0.28
    ():
    0.28
    $:
    0.28
    nam
    0.27
    Activations Density 0.906%

    No Known Activations