© 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. 113200
    Prev
    Next
    INDEX
    Explanations

    mexican

    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
     Ir
    -0.12
    weis
    -0.11
    pher
    -0.09
    atore
    -0.09
     sponsored
    -0.09
    ник
    -0.09
    Je
    -0.09
     distributed
    -0.09
     Jail
    -0.09
    bery
    -0.09
    POSITIVE LOGITS
    ocr
    0.10
     mash
    0.10
    RS
    0.09
     ugl
    0.09
    ache
    0.09
    cape
    0.08
     sensitivity
    0.08
    -type
    0.08
    Obs
    0.08
     Grove
    0.08
    Activations Density 0.001%

    No Known Activations