© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2473
    Prev
    Next
    INDEX
    Explanations

    AP followed by punctuation or specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hol
    -0.10
    cha
    -0.09
    iele
    -0.09
     aud
    -0.09
     bite
    -0.09
     contempor
    -0.09
     cha
    -0.09
    chg
    -0.09
     Cha
    -0.09
    HK
    -0.09
    POSITIVE LOGITS
    gar
    0.11
     Cow
    0.10
    ollo
    0.09
    ipop
    0.09
    portion
    0.08
     cow
    0.08
     nowrap
    0.08
    /ap
    0.08
    pliance
    0.08
    gre
    0.08
    Activations Density 0.145%

    No Known Activations