© 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. 5627
    Prev
    Next
    INDEX
    Explanations

    over, reading, patterns

    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
    –↵↵
    -0.13
     Feinstein
    -0.12
    ilyn
    -0.12
     setStatus
    -0.12
    chine
    -0.11
    ouri
    -0.11
    ajs
    -0.11
     Harper
    -0.11
    rimon
    -0.11
    resher
    -0.11
    POSITIVE LOGITS
     onto
    0.09
     Ult
    0.07
     her
    0.07
     backwards
    0.07
     ult
    0.06
     sideways
    0.06
     him
    0.06
     over
    0.06
     his
    0.06
     rooft
    0.06
    Activations Density 0.001%

    No Known Activations