© 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. 114889
    Prev
    Next
    INDEX
    Explanations

    end of list or sentence

    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
    jer
    -0.10
     assorted
    -0.10
     labeled
    -0.10
     oddly
    -0.09
     referenced
    -0.09
     Downing
    -0.09
     Herr
    -0.09
     Pretty
    -0.09
     Granted
    -0.09
     Seiten
    -0.09
    POSITIVE LOGITS
     splitted
    0.17
    Meanwhile
    0.12
    Apart
    0.12
    -supported
    0.12
     meanwhile
    0.11
     Apart
    0.11
     meantime
    0.11
     wrongly
    0.11
    (ii
    0.11
     favourable
    0.11
    Activations Density 0.064%

    No Known Activations