© 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. 115573
    Prev
    Next
    INDEX
    Explanations

    carrying and dropping items

    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
     Lun
    -0.12
    fst
    -0.11
    895
    -0.10
     Imported
    -0.10
    issen
    -0.10
     Lorem
    -0.10
     arbit
    -0.10
     substance
    -0.10
     lun
    -0.10
    unpack
    -0.10
    POSITIVE LOGITS
     stead
    0.12
     prec
    0.12
     precarious
    0.11
     awkward
    0.11
     Balance
    0.11
     balanced
    0.11
     balance
    0.10
     overloaded
    0.10
     Ferry
    0.10
     imbalance
    0.10
    Activations Density 0.056%

    No Known Activations