© 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. 89320
    Prev
    Next
    INDEX
    Explanations

    We.Retail, Weisberg, What We Love, We Gotta, We Are Cult

    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
     Hussein
    -0.11
    otas
    -0.10
    abad
    -0.10
     Bite
    -0.10
    oppel
    -0.10
    esti
    -0.10
    osten
    -0.10
    antz
    -0.10
    äº
    -0.09
    .docs
    -0.09
    POSITIVE LOGITS
     Perry
    0.08
     Kata
    0.08
    GET
    0.08
     unified
    0.08
    bsite
    0.08
     humans
    0.08
     optimized
    0.08
     decided
    0.07
     nit
    0.07
    formed
    0.07
    Activations Density 0.013%

    No Known Activations