© 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. 56681
    Prev
    Next
    INDEX
    Explanations

    introduction

    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
     sexual
    -0.08
     Sexual
    -0.07
    /Core
    -0.07
    è´§
    -0.07
    ughter
    -0.07
    sexual
    -0.07
     OM
    -0.06
     marry
    -0.06
    exual
    -0.06
    onical
    -0.06
    POSITIVE LOGITS
     Scri
    0.10
    uzz
    0.09
     operative
    0.09
     elev
    0.09
    indows
    0.09
    ikon
    0.09
    wig
    0.09
    lap
    0.09
     Validators
    0.09
    ctp
    0.09
    Activations Density 0.001%

    No Known Activations