© 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. 32936
    Prev
    Next
    INDEX
    Explanations

    's note

    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
    iten
    -0.11
    istani
    -0.11
    hood
    -0.10
    inish
    -0.09
    iform
    -0.09
     similarity
    -0.09
    ular
    -0.09
     similarities
    -0.09
    ento
    -0.09
     Bak
    -0.09
    POSITIVE LOGITS
     note
    0.20
    note
    0.16
     Note
    0.15
     notes
    0.15
     Notes
    0.12
     comment
    0.12
    Note
    0.12
     comments
    0.11
     Comment
    0.11
     NOTES
    0.11
    Activations Density 0.021%

    No Known Activations