© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 13838
    Prev
    Next
    INDEX
    Explanations

    repeated 'a' characters

    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
    Negative Logits
    a
    -0.08
    ulg
    -0.08
     prov
    -0.08
    flix
    -0.08
    Debugger
    -0.08
    urb
    -0.07
    ivals
    -0.07
    fac
    -0.07
    ixin
    -0.07
    lei
    -0.07
    POSITIVE LOGITS
    olini
    0.11
    ieri
    0.10
    -chan
    0.10
    hea
    0.10
    .lazy
    0.10
    ahlen
    0.10
    ertia
    0.10
    worth
    0.10
    waves
    0.10
    Lite
    0.10
    Activations Density 0.026%

    No Known Activations