© 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. 25921
    Prev
    Next
    INDEX
    Explanations

    } after code or section headers

    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
    quine
    -0.10
    baum
    -0.10
     dunk
    -0.09
    OOK
    -0.09
     lev
    -0.09
     podium
    -0.09
     *_
    -0.09
     *__
    -0.08
     ramp
    -0.08
     Royals
    -0.08
    POSITIVE LOGITS
     constructors
    0.11
     Constructors
    0.10
     wag
    0.10
     Wort
    0.10
    asser
    0.09
     Butt
    0.09
     Freund
    0.09
     Wag
    0.09
     Glad
    0.09
     Proud
    0.09
    Activations Density 0.006%

    No Known Activations