© 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. 3645
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    _abort
    -0.23
    íĶĦë¡ľê·¸
    -0.21
     presentViewController
    -0.21
    çĥĿ
    -0.21
    ylabel
    -0.20
    :black
    -0.20
    untu
    -0.19
    âģİ
    -0.19
     (!((
    -0.19
    ãĥIJãĥ¬
    -0.19
    POSITIVE LOGITS
     fick
    0.22
    keterangan
    0.20
     scaleY
    0.20
    ToString
    0.19
    addAction
    0.19
     Púb
    0.19
     Hath
    0.19
     salopes
    0.19
    кÑģи
    0.19
    NullException
    0.18
    Activations Density 0.129%

    No Known Activations