© 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. 33366
    Prev
    Next
    INDEX
    Explanations

    code header uniform

    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
    dfa
    -0.10
    agers
    -0.10
     Orr
    -0.10
     besides
    -0.10
    лÑİÑĩ
    -0.09
    hes
    -0.09
    AMS
    -0.09
     transitional
    -0.09
    gerald
    -0.09
     pack
    -0.09
    POSITIVE LOGITS
     purs
    0.09
     Bauer
    0.09
    ento
    0.08
    irth
    0.08
     Bain
    0.08
    /network
    0.07
     Bair
    0.07
     naughty
    0.07
     Sik
    0.07
    ety
    0.07
    Activations Density 0.434%

    No Known Activations