© 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. 30883
    Prev
    Next
    INDEX
    Explanations

    commas or periods after okay

    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
     albeit
    -0.10
     Skyl
    -0.08
     seperate
    -0.08
     intens
    -0.08
     l
    -0.07
     Tess
    -0.07
     rainbow
    -0.07
     nest
    -0.07
     Jonas
    -0.07
    135
    -0.07
    POSITIVE LOGITS
     Tracks
    0.11
     Zub
    0.10
    /el
    0.10
     Southampton
    0.10
    unga
    0.10
    RuleContext
    0.10
     Raised
    0.09
    [at
    0.09
    ิà¸Ļ
    0.09
    Pont
    0.09
    Activations Density 0.007%

    No Known Activations