© 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. 17912
    Prev
    Next
    INDEX
    Explanations

    period

    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
     Burl
    -0.08
     pickup
    -0.07
     spanking
    -0.07
     lig
    -0.07
    alg
    -0.07
     ears
    -0.07
     intimid
    -0.07
    Containing
    -0.07
     abdomen
    -0.06
     Roots
    -0.06
    POSITIVE LOGITS
     Sche
    0.13
     essence
    0.13
     ess
    0.13
    ess
    0.13
    antis
    0.12
    idl
    0.12
     displaced
    0.12
     dese
    0.12
    idel
    0.12
     frustrated
    0.12
    Activations Density 0.026%

    No Known Activations