© 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. 90392
    Prev
    Next
    INDEX
    Explanations

    people and groups

    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
    etal
    -0.12
    phis
    -0.11
     Bark
    -0.11
    oris
    -0.11
    rios
    -0.11
     liberties
    -0.11
     hers
    -0.11
    mys
    -0.10
     stirring
    -0.10
    swith
    -0.10
    POSITIVE LOGITS
    se
    0.09
     perceived
    0.08
    uit
    0.08
     outside
    0.08
     rang
    0.08
     Cant
    0.07
     deemed
    0.07
     reputed
    0.06
     qualified
    0.06
    este
    0.06
    Activations Density 0.234%

    No Known Activations