© 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. 29234
    Prev
    Next
    INDEX
    Explanations

    Bank of

    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
     Gateway
    -0.09
    lug
    -0.09
    lijk
    -0.09
     Respons
    -0.09
    966
    -0.09
     Drill
    -0.09
     Rico
    -0.09
     Boot
    -0.08
    bib
    -0.08
    -Class
    -0.08
    POSITIVE LOGITS
     banks
    0.13
     bank
    0.12
     Banks
    0.11
    stype
    0.11
     sunlight
    0.10
     banking
    0.10
     fog
    0.10
    banks
    0.10
     BANK
    0.10
     reservoir
    0.10
    Activations Density 0.025%

    No Known Activations