© 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. 1842
    Prev
    Next
    INDEX
    Explanations

    beginning sentences

    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
     currently
    -0.44
    缮åīį
    -0.42
    currently
    -0.40
     Currently
    -0.40
    Currently
    -0.36
     presently
    -0.33
    缮åīįæŃ£åľ¨
    -0.33
    çİ°éĺ¶æ®µ
    -0.30
     current
    -0.29
    ä»ĬæĻļ
    -0.29
    POSITIVE LOGITS
    å½ĵæŶ
    0.73
    å½ĵæŶçļĦ
    0.72
    æĪijå½ĵæŶ
    0.56
     was
    0.56
    çķ¶æĻĤ
    0.53
    æŶ任
    0.51
    was
    0.49
     wasn
    0.47
    åIJİæĿ¥
    0.46
    éĤ£æŶ
    0.45
    Activations Density 9.459%

    No Known Activations