© 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. 28457
    Prev
    Next
    INDEX
    Explanations

    the problem is how to

    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
     Abram
    -0.08
     Dub
    -0.08
     volta
    -0.08
     Pole
    -0.07
    aban
    -0.07
     unsuccessful
    -0.07
     metic
    -0.07
    lok
    -0.07
     critique
    -0.07
    xon
    -0.07
    POSITIVE LOGITS
     how
    0.23
    how
    0.22
     finding
    0.21
     reconc
    0.21
     figuring
    0.21
     How
    0.19
     Finding
    0.18
    How
    0.18
     whether
    0.18
     HOW
    0.18
    Activations Density 0.492%

    No Known Activations