© 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. 3388
    Prev
    Next
    INDEX
    Explanations

    lists or classifications

    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
    VOKE
    -0.22
    .BLL
    -0.21
     omas
    -0.20
    åļħ
    -0.20
    æĦ«
    -0.20
    même
    -0.20
    æĹ°
    -0.20
     èĭ¥è¦ģ
    -0.19
    imizer
    -0.18
    تاØŃ
    -0.18
    POSITIVE LOGITS
    arrings
    0.23
    ocene
    0.20
    ursday
    0.20
     minY
    0.19
    icare
    0.19
    è¤Ĥ
    0.19
    preci
    0.18
    chos
    0.18
    FileChooser
    0.18
    FormField
    0.18
    Activations Density 0.002%

    No Known Activations