© 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. 91784
    Prev
    Next
    INDEX
    Explanations

    free download

    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
     interviewed
    -0.08
     Makeup
    -0.08
     incompet
    -0.07
     thirsty
    -0.07
    iola
    -0.07
    mol
    -0.07
     mol
    -0.07
     bureaucr
    -0.07
    /per
    -0.07
    Ä°
    -0.07
    POSITIVE LOGITS
     gratis
    0.13
     downloaded
    0.12
     downloads
    0.12
     mỼi
    0.12
     Kostenlos
    0.12
    gratis
    0.11
     kostenlos
    0.11
     rar
    0.11
     free
    0.11
    _download
    0.11
    Activations Density 0.001%

    No Known Activations