© 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. 25687
    Prev
    Next
    INDEX
    Explanations

    at corner of

    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
    eler
    -0.09
    ief
    -0.09
     Hipp
    -0.08
    OCR
    -0.08
    851
    -0.08
    ique
    -0.08
    SAFE
    -0.08
     Bran
    -0.07
     females
    -0.07
    erra
    -0.07
    POSITIVE LOGITS
     between
    0.23
    ä¸İ
    0.22
    between
    0.20
     Between
    0.18
     zwischen
    0.18
     relationship
    0.17
    Between
    0.16
     duo
    0.16
     couples
    0.15
     BETWEEN
    0.15
    Activations Density 0.631%

    No Known Activations