© 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. 32860
    Prev
    Next
    INDEX
    Explanations

    end of

    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
    778
    -0.10
    olle
    -0.10
    hawk
    -0.10
    enberg
    -0.09
    oom
    -0.09
    acha
    -0.09
    uncan
    -0.09
    ).__
    -0.09
     whose
    -0.09
    umble
    -0.09
    POSITIVE LOGITS
     Cand
    0.09
     Cuisine
    0.08
     Noir
    0.08
     Lu
    0.08
     inex
    0.08
    -null
    0.08
     Fatal
    0.08
    -names
    0.07
     Chad
    0.07
     flush
    0.07
    Activations Density 0.070%

    No Known Activations