© 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. 750
    Prev
    Next
    INDEX
    Explanations

    side kiq, question, of, note, effects

    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
    ima
    -0.10
    ome
    -0.10
    omb
    -0.10
    (er
    -0.10
    Cow
    -0.10
    apolis
    -0.10
    legs
    -0.10
     floors
    -0.10
    egen
    -0.09
    lf
    -0.09
    POSITIVE LOGITS
    kick
    0.16
     hustle
    0.12
    -side
    0.11
     side
    0.11
    band
    0.11
     effects
    0.11
    è¾
    0.10
    burn
    0.10
     Effects
    0.10
    side
    0.10
    Activations Density 0.685%

    No Known Activations