© 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. 6176
    Prev
    Next
    INDEX
    Explanations

    sherbet, sherrod, sherell

    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
    irth
    -0.11
    ipsis
    -0.10
     immobil
    -0.10
    irs
    -0.09
    ori
    -0.09
     ramps
    -0.09
    sans
    -0.09
    orous
    -0.09
    ibil
    -0.09
    ors
    -0.09
    POSITIVE LOGITS
    ries
    0.11
    rier
    0.10
    ding
    0.10
    enco
    0.10
    rets
    0.09
    riers
    0.09
    ds
    0.09
    rieb
    0.09
    amient
    0.09
    /is
    0.09
    Activations Density 0.040%

    No Known Activations