© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16130
    Prev
    Next
    INDEX
    Explanations

    description, url, status, uuid

    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
     Pearce
    -0.08
    ismic
    -0.08
    legs
    -0.08
     McD
    -0.08
     yok
    -0.08
    IRTH
    -0.08
     chuck
    -0.08
    deen
    -0.08
    UNK
    -0.08
     solid
    -0.07
    POSITIVE LOGITS
     occasion
    0.11
    bih
    0.09
     vill
    0.09
    @admin
    0.09
     Olsen
    0.08
     bid
    0.08
     installs
    0.08
     nevertheless
    0.08
    Occurred
    0.08
     beneficiary
    0.08
    Activations Density 0.199%

    No Known Activations