© 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. 6406
    Prev
    Next
    INDEX
    Explanations

    particular, comments, Brandon, 19

    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
    ie
    -0.07
    olie
    -0.06
     respective
    -0.06
    856
    -0.06
     pep
    -0.06
     organizer
    -0.06
     DIM
    -0.06
     organizing
    -0.06
     retaliation
    -0.06
     indirectly
    -0.06
    POSITIVE LOGITS
     lul
    0.12
    ysi
    0.11
     masse
    0.11
    inton
    0.11
     eos
    0.11
     TAM
    0.11
    /design
    0.11
    uos
    0.11
     lain
    0.11
    suite
    0.11
    Activations Density 0.001%

    No Known Activations