© 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. 113641
    Prev
    Next
    INDEX
    Explanations

    as much as

    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
    olo
    -0.11
     Fol
    -0.11
     suffice
    -0.10
    –and
    -0.10
    olg
    -0.10
     whence
    -0.10
    zy
    -0.10
    ÑģÑĤÑĮ
    -0.09
    iren
    -0.09
    shiv
    -0.09
    POSITIVE LOGITS
     ness
    0.09
     pil
    0.09
     mutually
    0.09
     pant
    0.08
     fir
    0.08
    .lab
    0.08
     Towers
    0.08
     Hartford
    0.08
    .sup
    0.08
    ango
    0.08
    Activations Density 0.008%

    No Known Activations