© 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. 3383
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     Girlfriend
    -0.21
    	fflush
    -0.21
    '].$
    -0.21
    æįķé±¼
    -0.20
     Ging
    -0.20
    .Pattern
    -0.20
    åľ¨è¿ĩ渡
    -0.20
     GIR
    -0.19
    _due
    -0.18
    ÐļÑĥпиÑĤÑĮ
    -0.18
    POSITIVE LOGITS
    ='<?
    0.22
    setImage
    0.21
    upe
    0.21
    ubbo
    0.21
    akens
    0.21
    riott
    0.19
    arna
    0.19
    meye
    0.19
    ettings
    0.19
    cstdint
    0.19
    Activations Density 0.001%

    No Known Activations