© 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. 28171
    Prev
    Next
    INDEX
    Explanations

    donate to support

    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
     communities
    -0.10
     invitation
    -0.09
     community
    -0.09
     courage
    -0.09
     sunlight
    -0.09
    HAM
    -0.09
    community
    -0.08
    532
    -0.08
     automatically
    -0.08
    ham
    -0.08
    POSITIVE LOGITS
    ehler
    0.11
     safeg
    0.10
    ouro
    0.09
    azio
    0.09
    /Layout
    0.09
    -Russian
    0.09
    ollider
    0.09
    /exec
    0.09
    umi
    0.09
    /Area
    0.09
    Activations Density 0.019%

    No Known Activations