© 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. 4843
    Prev
    Next
    INDEX
    Explanations

    to discuss, to create, to achieve

    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
    ARED
    -0.10
    _none
    -0.09
     spare
    -0.08
     aforementioned
    -0.08
     nov
    -0.08
     oppose
    -0.08
     none
    -0.08
     supervise
    -0.08
     Refer
    -0.08
     twenty
    -0.08
    POSITIVE LOGITS
     utilizing
    0.11
     indeb
    0.11
     utilize
    0.11
     pickup
    0.11
     utilized
    0.10
     mange
    0.10
     actually
    0.10
     utilizes
    0.10
     inst
    0.10
    util
    0.10
    Activations Density 0.434%

    No Known Activations