© 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. 29264
    Prev
    Next
    INDEX
    Explanations

    newsletter or end

    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
    ahan
    -0.10
     Aber
    -0.09
     Bry
    -0.09
    isko
    -0.09
     quieter
    -0.08
    tram
    -0.08
    HB
    -0.08
    mos
    -0.08
    ted
    -0.08
    jem
    -0.08
    POSITIVE LOGITS
    ))==
    0.09
    >>(
    0.09
    oodoo
    0.09
     Keeper
    0.09
     Hooks
    0.09
    wis
    0.09
    cot
    0.09
     kut
    0.09
     Sir
    0.08
    alc
    0.08
    Activations Density 0.009%

    No Known Activations