© 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. 89839
    Prev
    Next
    INDEX
    Explanations

    medical sections, references

    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
     Shoe
    -0.11
    @qq
    -0.10
    undy
    -0.10
     indefinitely
    -0.09
     Geo
    -0.09
    CEE
    -0.09
     picking
    -0.09
    uchi
    -0.08
    .Net
    -0.08
     Tie
    -0.08
    POSITIVE LOGITS
     ringing
    0.10
    RELATED
    0.09
    aged
    0.09
    ("""
    0.09
    ict
    0.09
     Mell
    0.09
     filmy
    0.09
     Poz
    0.09
    ä¹Ī
    0.09
    OLT
    0.08
    Activations Density 0.044%

    No Known Activations