© 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. 91226
    Prev
    Next
    INDEX
    Explanations

    I realize this

    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
     somehow
    -0.11
     MUCH
    -0.10
    632
    -0.10
     commune
    -0.10
     Somehow
    -0.10
     Latter
    -0.10
     Glad
    -0.10
     Sherlock
    -0.10
     Vie
    -0.10
    120
    -0.10
    POSITIVE LOGITS
    may
    0.10
     fully
    0.09
     there
    0.09
     needing
    0.09
     perfectly
    0.09
     Evan
    0.09
    ool
    0.08
     admittedly
    0.08
    idan
    0.08
     risks
    0.08
    Activations Density 0.068%

    No Known Activations