© 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. 15992
    Prev
    Next
    INDEX
    Explanations

    what kind/can/is/that/have/if/about

    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
     Alternative
    -0.09
     outright
    -0.09
    inia
    -0.09
     motives
    -0.09
     Farr
    -0.08
    059
    -0.08
    inge
    -0.08
    rote
    -0.08
     why
    -0.08
     compensated
    -0.08
    POSITIVE LOGITS
    aja
    0.11
    illi
    0.11
     kinda
    0.11
     kind
    0.10
     unseen
    0.10
    abad
    0.10
     sort
    0.10
     extrem
    0.09
    -corner
    0.09
     inequalities
    0.09
    Activations Density 0.065%

    No Known Activations