© 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. 17913
    Prev
    Next
    INDEX
    Explanations

    purpose of this/the

    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
     recept
    -0.09
    ana
    -0.08
     reception
    -0.08
     prin
    -0.08
    inn
    -0.08
    rieb
    -0.08
    printer
    -0.08
     Deliver
    -0.08
    anth
    -0.08
    standing
    -0.08
    POSITIVE LOGITS
     existence
    0.16
     visits
    0.12
     visit
    0.12
     ende
    0.11
     endeavors
    0.11
     Visit
    0.11
     exercises
    0.11
     redesign
    0.11
    fos
    0.11
     exercise
    0.10
    Activations Density 0.253%

    No Known Activations