© 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. 112648
    Prev
    Next
    INDEX
    Explanations

    URLs and domain names

    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
     trot
    -0.11
    "&
    -0.10
    iew
    -0.10
     laps
    -0.10
    Synopsis
    -0.09
     Callback
    -0.09
    +i
    -0.09
    hani
    -0.09
     amps
    -0.09
    ascus
    -0.09
    POSITIVE LOGITS
     dep
    0.08
     enterprise
    0.08
    -old
    0.07
    fortune
    0.07
     unspecified
    0.07
    caster
    0.07
     Gardner
    0.07
     caster
    0.07
    200
    0.07
    fer
    0.07
    Activations Density 0.002%

    No Known Activations