© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32677
    Prev
    Next
    INDEX
    Explanations

    digging up, in, down, through

    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
    zon
    -0.10
     upright
    -0.10
    uns
    -0.09
     Lamb
    -0.09
    lington
    -0.09
     preserved
    -0.09
     kept
    -0.09
    osphere
    -0.09
     shield
    -0.09
    stk
    -0.09
    POSITIVE LOGITS
     trenches
    0.13
     heels
    0.13
     fingers
    0.12
     fing
    0.11
     finger
    0.11
     nails
    0.11
     elbows
    0.10
     thumbnails
    0.10
     heel
    0.10
     wells
    0.10
    Activations Density 0.005%

    No Known Activations