© 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. 2582
    Prev
    Next
    INDEX
    Explanations

    In contrast / In order

    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
    AMB
    -0.10
     Pom
    -0.10
     distur
    -0.10
    (Have
    -0.10
    izin
    -0.09
     Yours
    -0.09
     fairness
    -0.09
    ë¡
    -0.09
    ><![
    -0.09
    lobals
    -0.09
    POSITIVE LOGITS
     contra
    0.08
    nth
    0.08
    cz
    0.07
     sorte
    0.07
     CONTR
    0.07
    ,"↵
    0.07
    Wr
    0.07
    Lv
    0.07
    him
    0.07
     remed
    0.07
    Activations Density 0.140%

    No Known Activations