© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1632
    Prev
    Next
    INDEX
    Explanations

    quotes and writing

    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
    åݾ
    -0.30
    忸
    -0.29
    ("<?
    -0.28
    /respond
    -0.27
    æı¶
    -0.27
    æIJĽ
    -0.26
     modalitÃł
    -0.26
    çĿ¨
    -0.25
    titleLabel
    -0.24
    =fopen
    -0.24
    POSITIVE LOGITS
    requete
    0.29
     words
    0.27
     ($.
    0.26
    è¯Ń
    0.26
    åĨħ容
    0.26
     fontStyle
    0.25
     createSelector
    0.25
    é»ijæģ¶
    0.25
     statement
    0.24
    âĬĩ
    0.24
    Activations Density 3.888%

    No Known Activations