© 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. 28047
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or names

    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
    oud
    -0.09
     Citizenship
    -0.09
     Parad
    -0.09
     Bez
    -0.07
     rest
    -0.07
     paradigm
    -0.07
    cret
    -0.07
    аÑĢÑĤ
    -0.07
     Counter
    -0.07
     disclose
    -0.07
    POSITIVE LOGITS
     ornament
    0.12
    nas
    0.11
    evin
    0.11
    ë²Ī
    0.10
    Seconds
    0.10
    ewis
    0.10
     Phelps
    0.10
    .zip
    0.10
     domin
    0.10
    efe
    0.10
    Activations Density 0.014%

    No Known Activations