© 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. 115727
    Prev
    Next
    INDEX
    Explanations

    frequently asked questions

    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
     conditioning
    -0.09
    nels
    -0.09
     wyst
    -0.09
     satur
    -0.09
    owy
    -0.09
     Conditioning
    -0.09
     communal
    -0.09
     Dow
    -0.09
     conditioned
    -0.08
    pes
    -0.08
    POSITIVE LOGITS
     sneak
    0.09
    ures
    0.09
     questions
    0.09
    alen
    0.09
    ueur
    0.09
     jos
    0.08
    uest
    0.08
     oft
    0.08
     lite
    0.08
    umen
    0.08
    Activations Density 0.004%

    No Known Activations