© 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. 91978
    Prev
    Next
    INDEX
    Explanations

    number or quantity descriptor

    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
     COPYING
    -0.09
    &a
    -0.09
     gele
    -0.09
    -Disposition
    -0.08
     Kind
    -0.08
    обÑĭ
    -0.08
    ussion
    -0.08
     Bauer
    -0.08
     Thor
    -0.08
    perature
    -0.08
    POSITIVE LOGITS
     aforementioned
    0.14
    -ing
    0.10
     Mercer
    0.10
    -turned
    0.09
     afore
    0.09
     indeed
    0.08
    ified
    0.08
     ing
    0.08
     Jes
    0.08
     Mons
    0.08
    Activations Density 0.317%

    No Known Activations