© 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. 16081
    Prev
    Next
    INDEX
    Explanations

    it

    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
    isha
    -0.10
    azzo
    -0.09
     propos
    -0.09
     shortcut
    -0.09
     predicate
    -0.09
     predicates
    -0.09
    esta
    -0.09
    nex
    -0.09
    467
    -0.08
    PLUS
    -0.08
    POSITIVE LOGITS
     Bravo
    0.10
    chy
    0.10
    acon
    0.10
    SCI
    0.10
    unes
    0.10
     selectively
    0.10
    iner
    0.09
     apar
    0.09
     blunt
    0.09
     herself
    0.09
    Activations Density 0.017%

    No Known Activations