© 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. 30646
    Prev
    Next
    INDEX
    Explanations

    promotion and promoted

    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
    ioso
    -0.11
    stream
    -0.11
    maid
    -0.11
    rement
    -0.11
    aver
    -0.10
    اء
    -0.10
    aves
    -0.10
    roid
    -0.10
    AVOR
    -0.09
    -relative
    -0.09
    POSITIVE LOGITS
    enade
    0.11
    ulg
    0.10
    etheus
    0.10
    (prom
    0.09
    ita
    0.08
    ein
    0.08
    ised
    0.08
    ç´ł
    0.08
    ção
    0.08
    arker
    0.08
    Activations Density 0.054%

    No Known Activations