© 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. 555
    Prev
    Next
    INDEX
    Explanations

    or its affiliates

    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
    /or
    -0.20
     NONINFRINGEMENT
    -0.11
    ataka
    -0.11
    rogen
    -0.10
    /OR
    -0.10
     hence
    -0.09
     therefore
    -0.09
     thereby
    -0.09
    ré
    -0.08
     thus
    -0.08
    POSITIVE LOGITS
    èĢħ
    0.37
    ients
    0.31
    phans
    0.31
     else
    0.28
    ifice
    0.28
     alternatively
    0.27
    acles
    0.26
    acular
    0.25
    ignal
    0.23
     equival
    0.23
    Activations Density 0.717%

    No Known Activations