© 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. 3795
    Prev
    Next
    INDEX
    Explanations

    appreciate any feedback or help

    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
     me
    -0.08
     Belt
    -0.08
    OSH
    -0.08
     Pes
    -0.07
    ugu
    -0.07
     searcher
    -0.07
     searched
    -0.07
     capacities
    -0.07
     demanded
    -0.07
     abl
    -0.07
    POSITIVE LOGITS
     feedback
    0.36
     Feedback
    0.30
    Feedback
    0.27
    feedback
    0.26
     comments
    0.25
     criticism
    0.23
     critiques
    0.22
    -feedback
    0.21
     constructive
    0.21
     Comments
    0.20
    Activations Density 0.060%

    No Known Activations