© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 897
    Prev
    Next
    INDEX
    Explanations

    researched verbs

    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
     ($("#
    -0.30
    éĩįè¦ģåĽłç´ł
    -0.23
     ($('#
    -0.22
    è¦ģéĹ»
    -0.22
    thora
    -0.22
    customerId
    -0.21
     CDDL
    -0.19
    æıł
    -0.19
    说ä»Ģä¹Ī
    -0.19
    PL
    -0.19
    POSITIVE LOGITS
     by
    0.28
    /cop
    0.27
     oleh
    0.27
    _by
    0.26
    %X
    0.25
    äºĨä¸Ģéģį
    0.24
    TED
    0.23
    ][_
    0.23
    (/^\
    0.22
    åĢĴåľ¨åľ°
    0.22
    Activations Density 2.483%

    No Known Activations