© 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. 115620
    Prev
    Next
    INDEX
    Explanations

    all the

    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
     Nic
    -0.10
     Contrast
    -0.09
     Gle
    -0.09
     Contr
    -0.08
     literal
    -0.08
    invert
    -0.08
     beat
    -0.08
    msp
    -0.08
    uem
    -0.08
    uat
    -0.08
    POSITIVE LOGITS
    roman
    0.09
     outing
    0.09
     sortable
    0.09
    eron
    0.09
    abile
    0.09
    arro
    0.09
     wanting
    0.09
    ix
    0.09
    (IR
    0.09
    unter
    0.09
    Activations Density 0.001%

    No Known Activations