© 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. 1374
    Prev
    Next
    INDEX
    Explanations

    Like followed by common 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
     like
    -0.11
     likes
    -0.09
     LIKE
    -0.08
    neh
    -0.08
    ickey
    -0.08
    Porno
    -0.08
    ihat
    -0.08
    æĪ
    -0.08
    respect
    -0.08
     å¦Ĥ
    -0.08
    POSITIVE LOGITS
    -minded
    0.29
     minded
    0.23
     unto
    0.17
    WISE
    0.15
    able
    0.15
    ewise
    0.14
    -wise
    0.13
     ours
    0.13
     yours
    0.12
     attracts
    0.12
    Activations Density 0.475%

    No Known Activations