© 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. 5331
    Prev
    Next
    INDEX
    Explanations

    only when

    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
     prematurely
    -0.10
    quat
    -0.09
     Continuous
    -0.09
    erten
    -0.08
     continua
    -0.08
    vl
    -0.08
    Continuous
    -0.08
     boldly
    -0.08
     continuous
    -0.08
    оÑģÑĮ
    -0.08
    POSITIVE LOGITS
     occasional
    0.72
     occasionally
    0.65
     Occasionally
    0.52
     periodically
    0.51
     spor
    0.50
     intermitt
    0.49
     intermittent
    0.41
     periodic
    0.41
     occas
    0.36
    Occ
    0.34
    Activations Density 0.465%

    No Known Activations