© 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. 88236
    Prev
    Next
    INDEX
    Explanations

    lists with: or — is

    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
     Kendall
    -0.10
     unknow
    -0.10
     someday
    -0.10
     confer
    -0.10
     invented
    -0.10
     secretly
    -0.10
    isses
    -0.09
     OUR
    -0.09
     Please
    -0.09
     imagined
    -0.09
    POSITIVE LOGITS
     nicely
    0.14
     plenty
    0.13
     impress
    0.13
     pretty
    0.13
     impressive
    0.13
     standout
    0.12
     decent
    0.12
     fairly
    0.12
    Overall
    0.12
     somewhat
    0.12
    Activations Density 0.085%

    No Known Activations