© 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. 17126
    Prev
    Next
    INDEX
    Explanations

    of interest

    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
     warranted
    -0.07
     warrant
    -0.07
    ajes
    -0.07
     detr
    -0.07
     Nar
    -0.07
    auf
    -0.07
    nahme
    -0.07
     moderately
    -0.06
     Egyptian
    -0.06
     philosoph
    -0.06
    POSITIVE LOGITS
     relevance
    0.13
     Mayo
    0.13
    rine
    0.13
    course
    0.13
     sorts
    0.12
     kind
    0.12
    /from
    0.12
     interest
    0.12
     category
    0.12
    inee
    0.12
    Activations Density 0.377%

    No Known Activations