© 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. 112250
    Prev
    Next
    INDEX
    Explanations

    describing attributes or states

    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
     ASAP
    -0.07
     Ard
    -0.07
     Turbo
    -0.07
     Va
    -0.07
     Tyson
    -0.07
     turbo
    -0.06
     Pole
    -0.06
     cott
    -0.06
     Vall
    -0.06
     TY
    -0.06
    POSITIVE LOGITS
     means
    0.27
     refers
    0.25
     meaning
    0.22
    means
    0.22
    ?
    0.22
     indeed
    0.21
     because
    0.20
     referring
    0.20
    ?!
    0.19
    because
    0.19
    Activations Density 0.245%

    No Known Activations