© 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. 5639
    Prev
    Next
    INDEX
    Explanations

    questions starting with what

    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
     primitive
    -0.10
     wh
    -0.09
     Mort
    -0.09
     prim
    -0.09
    [Index
    -0.08
     reg
    -0.08
     pr
    -0.08
     assigned
    -0.08
    hard
    -0.08
     whit
    -0.08
    POSITIVE LOGITS
     What
    0.14
    What
    0.13
     about
    0.13
     Does
    0.13
     noteworthy
    0.13
     About
    0.12
     surprising
    0.12
     Characteristics
    0.12
     Do
    0.12
     qualities
    0.11
    Activations Density 0.034%

    No Known Activations