© 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. 91405
    Prev
    Next
    INDEX
    Explanations

    revolutionized

    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
     irresistible
    -0.13
    aleb
    -0.12
    rees
    -0.11
    hos
    -0.11
    /at
    -0.10
     ebony
    -0.10
    ames
    -0.10
    asty
    -0.10
    pts
    -0.10
    -scal
    -0.10
    POSITIVE LOGITS
     Laure
    0.09
     Spotlight
    0.08
    collapse
    0.08
    ized
    0.08
    ike
    0.08
     sniff
    0.08
    eni
    0.08
     Panc
    0.08
     convergence
    0.07
     pressing
    0.07
    Activations Density 0.002%

    No Known Activations