© 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. 2044
    Prev
    Next
    INDEX
    Explanations

    PMethod 1Reason: The MAX_ACTIVATING_TOKENS are all variations of the letter 'P'.P

    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
    entiful
    -0.28
     !!}
    -0.23
    Ĥæķ°
    -0.21
    ViewInit
    -0.20
    casting
    -0.19
    .LA
    -0.19
    -UA
    -0.19
    >Returns
    -0.19
    SPATH
    -0.19
     GetById
    -0.18
    POSITIVE LOGITS
    еÑĢиал
    0.27
    éĻªä½ł
    0.21
    åİĨåı²æĸ°
    0.20
    éĴī
    0.19
    tron
    0.19
     '".$_
    0.19
    %;">↵
    0.18
     ("<
    0.18
    RelativeTo
    0.18
     zak
    0.18
    Activations Density 0.086%

    No Known Activations