© 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. 7051
    Prev
    Next
    INDEX
    Explanations

    sigh of relief

    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
     talks
    -0.09
     Laugh
    -0.09
     established
    -0.08
    assa
    -0.08
    GA
    -0.08
    ymes
    -0.08
     views
    -0.08
     acting
    -0.08
     Torch
    -0.08
     vic
    -0.08
    POSITIVE LOGITS
     erupt
    0.16
     invol
    0.15
     uttered
    0.15
     elic
    0.14
     escaping
    0.14
    utter
    0.14
     escaped
    0.13
     emitted
    0.13
     escape
    0.13
     provoked
    0.13
    Activations Density 0.044%

    No Known Activations