© 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. 50587
    Prev
    Next
    INDEX
    Explanations

    select

    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
    isser
    -0.10
    ToLocal
    -0.09
     Fol
    -0.09
    avras
    -0.09
     stagnant
    -0.09
     Shortly
    -0.09
     safeg
    -0.09
     scarce
    -0.09
    Seconds
    -0.09
     cons
    -0.09
    POSITIVE LOGITS
     selecting
    0.36
     whichever
    0.36
     selects
    0.35
     select
    0.34
     selected
    0.34
     selection
    0.31
     Select
    0.30
     Selection
    0.29
    Select
    0.28
     choosing
    0.28
    Activations Density 1.032%

    No Known Activations