© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4934
    Prev
    Next
    INDEX
    Explanations

    tapping and tap

    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
    Negative Logits
     bride
    -0.08
    ary
    -0.08
     blended
    -0.08
    chet
    -0.08
    ACES
    -0.08
    Executable
    -0.08
     Ferry
    -0.08
    ÅĦst
    -0.08
     bite
    -0.07
    æݨ
    -0.07
    POSITIVE LOGITS
    ur
    0.11
    ew
    0.10
    lage
    0.10
    ahn
    0.10
    pir
    0.10
    ovan
    0.09
    urst
    0.09
     tapping
    0.09
    oir
    0.09
    pra
    0.09
    Activations Density 0.129%

    No Known Activations