© 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. 48247
    Prev
    Next
    INDEX
    Explanations

    as compared to

    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
     sno
    -0.08
    een
    -0.08
    yb
    -0.08
    hor
    -0.07
    ihar
    -0.07
     Plays
    -0.07
    lias
    -0.07
     supposedly
    -0.07
    gens
    -0.07
     adher
    -0.07
    POSITIVE LOGITS
     earlier
    0.25
     usual
    0.24
     previous
    0.23
     previously
    0.22
     elsewhere
    0.20
     yesterday
    0.19
     Previously
    0.18
     before
    0.17
     Earlier
    0.17
    usual
    0.17
    Activations Density 0.164%

    No Known Activations