© 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. 5606
    Prev
    Next
    INDEX
    Explanations

    takes time or duration

    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
     Norton
    -0.11
    åľŁ
    -0.11
     distances
    -0.10
    ohana
    -0.10
    handled
    -0.10
     Niet
    -0.10
    TMP
    -0.10
     Reyes
    -0.10
    /small
    -0.10
    VT
    -0.10
    POSITIVE LOGITS
     longer
    0.19
     awhile
    0.17
     Longer
    0.14
     us
    0.11
     longest
    0.11
     forever
    0.11
     months
    0.11
     weeks
    0.10
     MONTH
    0.10
     precedence
    0.09
    Activations Density 0.031%

    No Known Activations