© 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. 26990
    Prev
    Next
    INDEX
    Explanations

    how much 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
    itr
    -0.10
     preferences
    -0.09
     Col
    -0.09
    lore
    -0.09
     Economics
    -0.09
    fait
    -0.09
     cere
    -0.08
    hek
    -0.08
     substantive
    -0.08
    .col
    -0.08
    POSITIVE LOGITS
     charged
    0.10
     Charge
    0.10
     Weed
    0.09
     charge
    0.09
     pinch
    0.09
    arat
    0.09
    orig
    0.09
     wig
    0.09
     Charg
    0.09
     TOO
    0.09
    Activations Density 0.057%

    No Known Activations