© 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. 5687
    Prev
    Next
    INDEX
    Explanations

    percentage values

    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
    etti
    -0.08
    olio
    -0.07
    apl
    -0.07
    CHED
    -0.07
     concentration
    -0.07
    ocket
    -0.07
    oa
    -0.06
    oul
    -0.06
    rena
    -0.06
     Wid
    -0.06
    POSITIVE LOGITS
     pane
    0.11
     bols
    0.11
     Bauer
    0.10
    Bins
    0.10
     MOT
    0.10
     Wilkinson
    0.10
     Laud
    0.10
    ENTE
    0.09
     Pole
    0.09
     OT
    0.09
    Activations Density 0.201%

    No Known Activations