© 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. 32413
    Prev
    Next
    INDEX
    Explanations

    is/was/are followed by descriptive words

    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
    ieux
    -0.11
     respective
    -0.10
    iou
    -0.09
     pent
    -0.09
     gentleman
    -0.09
    iks
    -0.08
     CONS
    -0.08
    vc
    -0.08
     Princip
    -0.08
     purposely
    -0.08
    POSITIVE LOGITS
     testament
    0.17
     contrast
    0.15
     icing
    0.13
     offset
    0.12
    matched
    0.12
     indicative
    0.12
    contrast
    0.12
     testimony
    0.12
     enough
    0.11
     complement
    0.11
    Activations Density 0.136%

    No Known Activations