© 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. 826
    Prev
    Next
    INDEX
    Explanations

    work and skills

    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
    1
    -0.31
    0
    -0.30
    2
    -0.27
    5
    -0.27
    3
    -0.26
    4
    -0.25
    6
    -0.25
    7
    -0.24
    9
    -0.23
    H
    -0.23
    POSITIVE LOGITS
    -ves
    0.36
     fkk
    0.34
    -With
    0.34
     (*((
    0.33
    "';
    0.33
    emsp
    0.33
    /↵↵↵↵
    0.32
    "<?
    0.32
    âļĹ
    0.31
    @dynamic
    0.31
    Activations Density 3.531%

    No Known Activations