© 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. 5728
    Prev
    Next
    INDEX
    Explanations

    Oliver Names

    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
    uhl
    -0.12
    "",
    -0.12
     Reporter
    -0.11
     TTL
    -0.11
    alf
    -0.11
     Realm
    -0.11
    canf
    -0.11
    Reporter
    -0.11
     bef
    -0.11
    ugi
    -0.11
    POSITIVE LOGITS
     Comp
    0.10
     Sunshine
    0.08
    igram
    0.07
     Roths
    0.07
     Goldberg
    0.07
    orde
    0.07
    spm
    0.07
     H
    0.06
     Asc
    0.06
     energ
    0.06
    Activations Density 0.003%

    No Known Activations