© 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. 4334
    Prev
    Next
    INDEX
    Explanations

    not ordinary or random

    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
     Alo
    -0.09
    extend
    -0.08
    redi
    -0.08
    —all
    -0.08
    UBE
    -0.08
    ings
    -0.07
     Oasis
    -0.07
    ibi
    -0.07
    gt
    -0.07
    ISC
    -0.07
    POSITIVE LOGITS
     ordinary
    0.40
     Ordinary
    0.31
    ordinary
    0.30
     arbitrary
    0.28
    any
    0.26
     any
    0.25
    Ord
    0.24
     ANY
    0.23
     Arbitrary
    0.23
     random
    0.21
    Activations Density 0.098%

    No Known Activations