© 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. 4644
    Prev
    Next
    INDEX
    Explanations

    Starting lists with punctuation

    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
     ide
    -0.09
    heard
    -0.08
    oder
    -0.08
    Feels
    -0.07
     felt
    -0.07
    agli
    -0.07
     odd
    -0.07
     occasional
    -0.07
    753
    -0.07
    ospel
    -0.07
    POSITIVE LOGITS
     Using
    0.25
     using
    0.23
    Using
    0.23
    Ignoring
    0.20
     ignoring
    0.20
     Without
    0.19
     Taking
    0.19
     reluctantly
    0.19
     USING
    0.19
     guided
    0.18
    Activations Density 0.451%

    No Known Activations