© 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. 112004
    Prev
    Next
    INDEX
    Explanations

    mus ings, culos, car, lin

    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
    arius
    -0.10
    ONS
    -0.09
    usz
    -0.08
     Sammy
    -0.08
    earing
    -0.08
    icers
    -0.08
    awn
    -0.08
    ons
    -0.07
    iddle
    -0.07
    aires
    -0.07
    POSITIVE LOGITS
     mus
    0.16
    cov
    0.14
    cling
    0.12
    cial
    0.11
    ically
    0.11
    culos
    0.11
    cid
    0.11
    ced
    0.11
    cade
    0.11
    occo
    0.11
    Activations Density 0.005%

    No Known Activations