© 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. 90485
    Prev
    Next
    INDEX
    Explanations

    url starters or disclaimers

    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
    afen
    -0.08
     boundary
    -0.08
     mus
    -0.08
     Partner
    -0.08
     illustrated
    -0.08
    -repeat
    -0.08
     partnered
    -0.08
    idos
    -0.08
    821
    -0.07
     Gul
    -0.07
    POSITIVE LOGITS
     regul
    0.12
    ibri
    0.10
     commissions
    0.10
     Cher
    0.10
    yen
    0.10
     rude
    0.10
     HAPP
    0.10
     Hull
    0.10
     ruthless
    0.10
    adders
    0.10
    Activations Density 0.001%

    No Known Activations