© 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. 14440
    Prev
    Next
    INDEX
    Explanations

    Ros names

    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
     lean
    -0.10
     cons
    -0.10
    emos
    -0.10
     reins
    -0.10
     swimming
    -0.10
    imens
    -0.09
    iento
    -0.09
     em
    -0.09
     Geoffrey
    -0.09
    ço
    -0.09
    POSITIVE LOGITS
    ifier
    0.08
    BUF
    0.08
     Pry
    0.08
     fulfillment
    0.08
    nee
    0.08
     appet
    0.08
     Dynam
    0.08
     maneuver
    0.08
    coe
    0.08
    EXPECTED
    0.08
    Activations Density 0.003%

    No Known Activations