© 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. 31723
    Prev
    Next
    INDEX
    Explanations

    back words

    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
    arten
    -0.11
     Gol
    -0.10
     tongue
    -0.09
    ackle
    -0.09
     lighten
    -0.09
     lo
    -0.09
    rys
    -0.09
     mime
    -0.09
     culp
    -0.09
     tong
    -0.09
    POSITIVE LOGITS
    /back
    0.10
    finity
    0.10
     bouncing
    0.10
    fat
    0.10
    assel
    0.09
    /big
    0.09
    -centric
    0.09
    ican
    0.09
     Rico
    0.09
    rack
    0.09
    Activations Density 0.006%

    No Known Activations