© 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. 88912
    Prev
    Next
    INDEX
    Explanations

    volume and quantity

    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
    vic
    -0.11
     sof
    -0.11
    364
    -0.11
     encuent
    -0.10
     decre
    -0.10
     Flam
    -0.10
     softly
    -0.10
    oso
    -0.10
    ",-
    -0.09
     doors
    -0.09
    POSITIVE LOGITS
     volume
    0.36
     volumes
    0.32
     quantity
    0.32
    volume
    0.29
     Volume
    0.29
     amount
    0.28
     volum
    0.27
     quantities
    0.27
    -volume
    0.26
    Volume
    0.26
    Activations Density 0.281%

    No Known Activations