© 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. 90427
    Prev
    Next
    INDEX
    Explanations

    list separatorscode keywordslist items

    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
    stadt
    -0.10
    insky
    -0.10
     (~(
    -0.10
    lijah
    -0.10
    midi
    -0.10
     various
    -0.10
     Mention
    -0.09
    (other
    -0.09
    stice
    -0.09
    veh
    -0.09
    POSITIVE LOGITS
    ober
    0.09
     bald
    0.09
     mo
    0.08
    DonaldTrump
    0.08
     internet
    0.08
    /categories
    0.08
     hobbies
    0.08
     testimonials
    0.08
     rant
    0.07
     commodities
    0.07
    Activations Density 0.016%

    No Known Activations