© 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. 5074
    Prev
    Next
    INDEX
    Explanations

    topics from a range

    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
     streak
    -0.10
     imposing
    -0.09
     compromising
    -0.08
     emitting
    -0.08
     stationed
    -0.08
     competent
    -0.07
     eup
    -0.07
     qualified
    -0.07
     equipped
    -0.07
     contrary
    -0.07
    POSITIVE LOGITS
     topics
    0.33
     Topics
    0.27
    topics
    0.25
    Topics
    0.24
     matters
    0.21
    /topics
    0.21
     discussing
    0.21
    topic
    0.21
     topic
    0.20
     sexuality
    0.20
    Activations Density 0.552%

    No Known Activations