© 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. 50514
    Prev
    Next
    INDEX
    Explanations

    @, by, email addresses, usernames

    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
    .—
    -0.10
    £
    -0.09
    ._
    -0.09
    —if
    -0.09
     coc
    -0.09
    adar
    -0.09
    —it
    -0.08
     canal
    -0.08
    —all
    -0.08
    ”—
    -0.08
    POSITIVE LOGITS
     Sting
    0.10
     irres
    0.10
     quasi
    0.10
     ([[
    0.09
     intox
    0.09
     [=
    0.09
    /{{
    0.09
     facile
    0.09
    aign
    0.08
     nto
    0.08
    Activations Density 0.003%

    No Known Activations