© 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. 15466
    Prev
    Next
    INDEX
    Explanations

    article beginnings

    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
     programme
    -0.07
    usan
    -0.07
     Sunrise
    -0.06
     Juni
    -0.06
     reproduction
    -0.06
     dis
    -0.06
     authorised
    -0.06
     programmes
    -0.06
     Joi
    -0.06
     Sav
    -0.06
    POSITIVE LOGITS
     The
    0.20
    The
    0.14
     There
    0.14
    >The
    0.13
     Those
    0.12
     When
    0.12
    	The
    0.12
     With
    0.12
    -The
    0.11
     It
    0.11
    Activations Density 0.159%

    No Known Activations