© 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. 935
    Prev
    Next
    INDEX
    Explanations

    .

    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
    ç¾İåªĴ
    -0.25
    abcdefghijkl
    -0.23
     pregn
    -0.23
     nomine
    -0.22
     tatto
    -0.22
    .ImageAlign
    -0.22
    建档ç«ĭ
    -0.21
     اÙĦاÙĨساÙĨ
    -0.21
    ">ÃĹ</
    -0.21
    gages
    -0.21
    POSITIVE LOGITS
    endtime
    0.26
    filtro
    0.25
    }elseif
    0.23
    èĩ£
    0.21
    vlc
    0.21
    ernet
    0.20
     ${({
    0.20
    çĶŃ
    0.20
    iner
    0.20
    prix
    0.20
    Activations Density 0.296%

    No Known Activations