© 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. 91809
    Prev
    Next
    INDEX
    Explanations

    tag cloud

    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
    ipi
    -0.10
     pie
    -0.08
    cie
    -0.07
    umin
    -0.07
     Pie
    -0.07
     slightest
    -0.07
    vider
    -0.07
     Wade
    -0.07
    burn
    -0.07
     MLM
    -0.07
    POSITIVE LOGITS
     tags
    0.15
     Tags
    0.14
     aka
    0.13
    Tags
    0.13
     tag
    0.13
    tags
    0.13
     tagging
    0.13
     tagName
    0.13
    (Tag
    0.12
    /tag
    0.12
    Activations Density 0.001%

    No Known Activations