© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6500
    Prev
    Next
    INDEX
    Explanations

    ERA, era, eras, Week

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urst
    -0.11
    arity
    -0.11
    arily
    -0.10
    ServletRequest
    -0.10
    azaar
    -0.09
     peripheral
    -0.09
    arith
    -0.09
    OOK
    -0.09
    erno
    -0.09
    wealth
    -0.09
    POSITIVE LOGITS
    entes
    0.10
    beros
    0.10
    iah
    0.09
    ity
    0.09
    uela
    0.09
    asmus
    0.09
    ixon
    0.09
    UGIN
    0.09
    andez
    0.09
    ault
    0.09
    Activations Density 0.280%

    No Known Activations