© 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. 31416
    Prev
    Next
    INDEX
    Explanations

    only $ or just $

    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
     cons
    -0.11
     unw
    -0.11
     integral
    -0.11
     billions
    -0.10
     seen
    -0.10
     clutch
    -0.10
     hundreds
    -0.10
     millions
    -0.10
     Millions
    -0.09
     bet
    -0.09
    POSITIVE LOGITS
    ï¿¥
    0.10
     monthly
    0.10
     remot
    0.09
     Monthly
    0.09
    oric
    0.09
    çĦ¡æĸĻ
    0.08
     Weld
    0.08
    ä½
    0.08
     Pall
    0.08
     freely
    0.08
    Activations Density 0.002%

    No Known Activations