© 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. 26577
    Prev
    Next
    INDEX
    Explanations

    turnturn offturn tables

    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
    unter
    -0.11
    ripp
    -0.10
    vely
    -0.10
    lek
    -0.09
    ingers
    -0.09
     Fuller
    -0.09
    oon
    -0.09
    ders
    -0.08
    dest
    -0.08
    gies
    -0.08
    POSITIVE LOGITS
    pike
    0.22
    stile
    0.17
    -around
    0.16
    tables
    0.14
    itin
    0.14
    about
    0.13
    table
    0.13
    ips
    0.12
    tabl
    0.12
    around
    0.11
    Activations Density 0.079%

    No Known Activations