© 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. 15954
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
     ordering
    -0.10
     Nimbus
    -0.10
    isz
    -0.10
     DAL
    -0.09
    zew
    -0.09
    IMS
    -0.09
    elib
    -0.09
     GK
    -0.08
    Saga
    -0.08
     Gast
    -0.08
    POSITIVE LOGITS
     plans
    0.10
     importantly
    0.10
     etc
    0.09
     ect
    0.09
    plan
    0.09
     Lancaster
    0.08
    illac
    0.08
    qc
    0.08
    uni
    0.08
     cinematic
    0.08
    Activations Density 0.031%

    No Known Activations