© 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. 1907
    Prev
    Next
    INDEX
    Explanations

    conjunctions or clauses

    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
    grily
    -0.31
    ?"↵↵↵↵
    -0.28
    :";č↵
    -0.26
    /*↵
    -0.23
    lescope
    -0.23
    ocre
    -0.22
    rchive
    -0.22
    éĤ£ä½ł
    -0.22
    以åıĬ
    -0.22
    åıĬåħ¶
    -0.22
    POSITIVE LOGITS
     if
    0.52
     when
    0.44
    æĹ¢çĦ¶
    0.41
     since
    0.40
    å¦Ĥæŀľ
    0.39
     while
    0.38
    éī´äºİ
    0.37
    when
    0.37
    	if
    0.36
     еÑģли
    0.36
    Activations Density 2.191%

    No Known Activations