© 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. 88792
    Prev
    Next
    INDEX
    Explanations

    customization and custom options

    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
     sniff
    -0.08
     prepared
    -0.08
     improvised
    -0.08
     targets
    -0.08
     strategies
    -0.08
     lines
    -0.08
     structured
    -0.08
     Tide
    -0.08
     solo
    -0.08
     abst
    -0.08
    POSITIVE LOGITS
     customization
    0.39
     customize
    0.33
     Customize
    0.31
    customize
    0.26
     custom
    0.26
    -custom
    0.25
     Custom
    0.25
     customizable
    0.24
    _customize
    0.24
    /custom
    0.24
    Activations Density 0.236%

    No Known Activations