© 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. 112616
    Prev
    Next
    INDEX
    Explanations

    technical components and parts

    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
    ikan
    -0.12
    HEMA
    -0.11
     Russ
    -0.11
     då
    -0.11
    -errors
    -0.11
    .aggregate
    -0.11
     ÑĤек
    -0.11
    lest
    -0.11
     Binder
    -0.11
     cascade
    -0.11
    POSITIVE LOGITS
     itself
    0.15
    ’s
    0.15
    's
    0.14
    —which
    0.08
    -induced
    0.07
    ‘s
    0.07
    orton
    0.07
    ’S
    0.07
     wil
    0.07
    egend
    0.07
    Activations Density 0.418%

    No Known Activations