© 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. 15052
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms

    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
    TestMethod
    -0.12
     POR
    -0.09
     Ori
    -0.09
    alto
    -0.09
    mlin
    -0.08
     kettle
    -0.08
    MZ
    -0.08
     BAM
    -0.08
     CPL
    -0.08
     ved
    -0.08
    POSITIVE LOGITS
    (N
    0.29
    [N
    0.27
    =N
    0.25
    /N
    0.24
    :N
    0.24
    ,N
    0.24
    <N
    0.23
    +N
    0.23
    *N
    0.23
    	N
    0.22
    Activations Density 4.295%

    No Known Activations