© 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. 31915
    Prev
    Next
    INDEX
    Explanations

    change in

    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
     Constit
    -0.11
    MSC
    -0.09
     Mell
    -0.09
     confines
    -0.09
     Gur
    -0.09
     fact
    -0.08
     Sweat
    -0.08
    iais
    -0.08
     Insights
    -0.08
    contexts
    -0.08
    POSITIVE LOGITS
    /of
    0.16
     fortunes
    0.15
     attitude
    0.12
     workload
    0.12
     behavior
    0.12
     demeanor
    0.12
     attitudes
    0.11
     behaviour
    0.11
     scenery
    0.11
     morale
    0.11
    Activations Density 0.354%

    No Known Activations