© 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. 31783
    Prev
    Next
    INDEX
    Explanations

    cognitive functioning and biases

    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
     Hog
    -0.10
     attaching
    -0.10
     #:
    -0.10
    este
    -0.10
     Jens
    -0.09
     onboard
    -0.09
    iron
    -0.09
    aps
    -0.09
     comps
    -0.09
    ensen
    -0.08
    POSITIVE LOGITS
     verm
    0.09
     slick
    0.09
    AtIndex
    0.08
    NEL
    0.08
     Wohn
    0.08
     smooth
    0.08
     Richie
    0.08
     Sek
    0.08
    OrNull
    0.08
    .fast
    0.08
    Activations Density 0.005%

    No Known Activations