© 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. 27487
    Prev
    Next
    INDEX
    Explanations

    know what or how

    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
     McCabe
    -0.12
    Boom
    -0.12
     homo
    -0.11
     indeb
    -0.11
     gall
    -0.11
    urse
    -0.10
     mono
    -0.10
     boyc
    -0.10
     carn
    -0.10
     hete
    -0.10
    POSITIVE LOGITS
     about
    0.17
     enough
    0.16
     what
    0.15
     About
    0.11
     how
    0.11
     nothing
    0.11
    about
    0.11
     much
    0.11
     intimately
    0.10
     lots
    0.10
    Activations Density 0.060%

    No Known Activations