© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27540
    Prev
    Next
    INDEX
    Explanations

    Game, Pakistan, Sri, roll, align

    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
     Suzuki
    -0.10
     Carnival
    -0.09
     urge
    -0.09
     scattered
    -0.09
     worst
    -0.08
     mature
    -0.08
    asin
    -0.08
     UNITED
    -0.08
     Dag
    -0.08
     puberty
    -0.08
    POSITIVE LOGITS
     Chatt
    0.11
     locales
    0.11
     Notices
    0.09
     Polic
    0.09
    ¤í
    0.09
    unist
    0.09
    jen
    0.09
    [ch
    0.09
     kettle
    0.09
    orget
    0.09
    Activations Density 0.001%

    No Known Activations