© 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. 49756
    Prev
    Next
    INDEX
    Explanations

    shopping! or comment

    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
    393
    -0.08
     fan
    -0.07
     Ele
    -0.07
     ele
    -0.07
    Extract
    -0.07
    obo
    -0.07
    .extract
    -0.07
    affer
    -0.06
     MI
    -0.06
     boot
    -0.06
    POSITIVE LOGITS
     pioneer
    0.14
     Pole
    0.14
     Pioneer
    0.14
     pioneers
    0.13
    &type
    0.13
     pole
    0.13
     pioneering
    0.13
    pole
    0.12
    kehr
    0.11
     transl
    0.11
    Activations Density 0.042%

    No Known Activations