© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27320
    Prev
    Next
    INDEX
    Explanations

    my links, demos, and points

    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
     (“
    -0.09
     asynchronously
    -0.09
     online
    -0.08
     wikipedia
    -0.08
     acl
    -0.08
     Fantasy
    -0.08
     fantas
    -0.07
     sucess
    -0.07
    fant
    -0.07
     [=
    -0.07
    POSITIVE LOGITS
     appreciated
    0.12
     Infos
    0.11
     EF
    0.11
     Resize
    0.11
     coco
    0.11
     backs
    0.10
     Apprec
    0.10
     Drain
    0.10
     infos
    0.10
     Rut
    0.10
    Activations Density 0.028%

    No Known Activations