© 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. 88724
    Prev
    Next
    INDEX
    Explanations

    took a look

    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
     priv
    -0.11
    loadModel
    -0.10
     prive
    -0.10
     HG
    -0.10
     QLD
    -0.10
    .Sin
    -0.10
    apolis
    -0.10
     Pruitt
    -0.10
     auth
    -0.10
     oss
    -0.10
    POSITIVE LOGITS
     pictures
    0.10
     took
    0.10
     Grab
    0.10
    ìĤ¬
    0.09
     grabs
    0.09
     photographs
    0.09
    æīĭ
    0.09
     notice
    0.09
     reluctantly
    0.09
     clothes
    0.09
    Activations Density 0.016%

    No Known Activations