© 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. 113324
    Prev
    Next
    INDEX
    Explanations

    all over

    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
    ume
    -0.13
    uler
    -0.12
    iero
    -0.12
    |$
    -0.11
    ivar
    -0.11
    atte
    -0.11
    uran
    -0.11
    uming
    -0.11
    /re
    -0.11
     halfway
    -0.11
    POSITIVE LOGITS
     imaginable
    0.08
    azu
    0.08
    asts
    0.07
     else
    0.07
     Shine
    0.06
     exposed
    0.06
    apr
    0.06
     HO
    0.06
     Body
    0.06
     auss
    0.06
    Activations Density 0.004%

    No Known Activations