© 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. 17027
    Prev
    Next
    INDEX
    Explanations

    crane, crust, Crump

    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
     Brennan
    -0.11
    enu
    -0.11
     pride
    -0.11
    chrom
    -0.10
    enna
    -0.10
    idy
    -0.10
    rr
    -0.09
     prac
    -0.09
    OrCreate
    -0.09
    ready
    -0.09
    POSITIVE LOGITS
    shaw
    0.13
    ITICAL
    0.12
    ystal
    0.12
    shaft
    0.12
    ulence
    0.11
    ème
    0.11
    asso
    0.10
    (cr
    0.10
    worthy
    0.10
    osten
    0.10
    Activations Density 0.189%

    No Known Activations