© 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. 27519
    Prev
    Next
    INDEX
    Explanations

    glo, Glo, Flo, SLO

    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
    yro
    -0.09
     Whip
    -0.09
     meas
    -0.09
     Canary
    -0.08
    eer
    -0.08
    ers
    -0.08
     Invite
    -0.08
     Bone
    -0.08
    ule
    -0.08
    bek
    -0.08
    POSITIVE LOGITS
     glo
    0.14
     Glo
    0.12
     Glover
    0.11
     encaps
    0.10
    ody
    0.10
    orda
    0.10
    oby
    0.10
     balance
    0.10
    roller
    0.10
    lobal
    0.10
    Activations Density 0.004%

    No Known Activations