© 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. 116300
    Prev
    Next
    INDEX
    Explanations

    search engine generates recommendations or suggestions

    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
     Inputs
    -0.11
     Addresses
    -0.10
     Ain
    -0.10
     participate
    -0.10
     pratic
    -0.10
     freely
    -0.10
     particip
    -0.10
    iÃŁ
    -0.09
     glo
    -0.09
     conventions
    -0.09
    POSITIVE LOGITS
     automatically
    0.26
     suggestions
    0.23
     Suggestions
    0.22
     recommendations
    0.21
    Suggestions
    0.21
     recommending
    0.21
     generates
    0.20
     intellig
    0.20
     Recomm
    0.19
     recommendation
    0.19
    Activations Density 1.037%

    No Known Activations