© 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. 28017
    Prev
    Next
    INDEX
    Explanations

    whether

    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
    upon
    -0.11
    äºİ
    -0.11
    uchi
    -0.11
     Chall
    -0.10
    ger
    -0.10
     olan
    -0.10
    own
    -0.10
    uml
    -0.10
    áŀ¶áŀ
    -0.10
     furthermore
    -0.10
    POSITIVE LOGITS
     how
    0.21
     why
    0.18
    how
    0.16
     whether
    0.15
    why
    0.13
    :
    0.12
     majority
    0.12
     till
    0.11
     Till
    0.11
     apart
    0.11
    Activations Density 0.185%

    No Known Activations