© 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. 91318
    Prev
    Next
    INDEX
    Explanations

    I think, I find

    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
    Dock
    -0.10
     lng
    -0.09
     terribly
    -0.09
     Dud
    -0.09
    056
    -0.09
     CONSTANT
    -0.09
    /cpp
    -0.09
     barg
    -0.09
     Buff
    -0.09
     Painting
    -0.09
    POSITIVE LOGITS
     sk
    0.11
    umer
    0.10
    sek
    0.09
    ovation
    0.09
     tent
    0.09
     foot
    0.09
    otas
    0.09
    inant
    0.08
    ocs
    0.08
     Dayton
    0.08
    Activations Density 0.002%

    No Known Activations