© 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. 17099
    Prev
    Next
    INDEX
    Explanations

    Cam and Cambridge

    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
     grate
    -0.10
     cris
    -0.10
    rant
    -0.10
    las
    -0.10
     indispens
    -0.09
     lul
    -0.09
    Localized
    -0.09
     VIEW
    -0.09
    cis
    -0.09
    lines
    -0.09
    POSITIVE LOGITS
     Garcia
    0.09
    uin
    0.08
     costing
    0.08
     Constructor
    0.08
     Costume
    0.08
    zilla
    0.08
     Master
    0.08
    oops
    0.08
    inda
    0.07
     reap
    0.07
    Activations Density 0.004%

    No Known Activations