© 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. 7371
    Prev
    Next
    INDEX
    Explanations

    subscribe to

    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
    impl
    -0.11
    abouts
    -0.11
     duly
    -0.10
    (CharSequence
    -0.10
     Mahm
    -0.10
     misuse
    -0.10
     cit
    -0.10
     slime
    -0.10
    ripe
    -0.10
     impl
    -0.10
    POSITIVE LOGITS
     subscribers
    0.09
     subscribing
    0.08
     pledges
    0.08
     to
    0.08
     twig
    0.08
    497
    0.07
     lifetime
    0.07
     Patton
    0.07
    /Private
    0.07
    /Peak
    0.07
    Activations Density 0.001%

    No Known Activations