© 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. 117136
    Prev
    Next
    INDEX
    Explanations

    size magnitude enormousness

    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
    ENO
    -0.12
     otherwise
    -0.10
    etting
    -0.10
    oret
    -0.10
    otherwise
    -0.10
    AML
    -0.09
    raison
    -0.09
     stalk
    -0.09
    lein
    -0.09
     Rodrig
    -0.09
    POSITIVE LOGITS
    ous
    0.16
    ously
    0.14
    huge
    0.11
     enorm
    0.11
     Huge
    0.10
    OUS
    0.10
     monstrous
    0.10
     HUGE
    0.09
     colossal
    0.09
    ingly
    0.09
    Activations Density 0.001%

    No Known Activations