© 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. 50263
    Prev
    Next
    INDEX
    Explanations

    help for individuals and communities

    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
     firstly
    -0.14
     Firstly
    -0.12
     Begins
    -0.11
     Imports
    -0.10
    iams
    -0.10
     Yours
    -0.10
    iam
    -0.09
     swiftly
    -0.09
     curs
    -0.09
     crud
    -0.09
    POSITIVE LOGITS
     safer
    0.10
     useful
    0.08
     potentially
    0.08
     Leo
    0.08
    fdb
    0.08
     benchmark
    0.08
    voucher
    0.08
     SCM
    0.08
     ner
    0.07
     easier
    0.07
    Activations Density 0.002%

    No Known Activations