© 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. 27100
    Prev
    Next
    INDEX
    Explanations

    against the norm

    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
    dens
    -0.09
    yne
    -0.09
     Fors
    -0.09
     searcher
    -0.09
    imore
    -0.08
    implicit
    -0.08
    ãĥģ
    -0.08
     lapse
    -0.08
    488
    -0.08
    mens
    -0.08
    POSITIVE LOGITS
     wall
    0.11
    å¢
    0.10
     fence
    0.10
     Wall
    0.09
     walls
    0.09
    inci
    0.09
    ce
    0.09
     collage
    0.09
    afc
    0.09
    ìłģ
    0.09
    Activations Density 0.006%

    No Known Activations