© 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. 17831
    Prev
    Next
    INDEX
    Explanations

    positive attributes

    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
     crud
    -0.13
    anvas
    -0.11
     Outs
    -0.11
     Furious
    -0.11
     disposable
    -0.10
     useless
    -0.10
     shitty
    -0.10
     screw
    -0.10
     humiliating
    -0.10
     Männer
    -0.10
    POSITIVE LOGITS
     gentle
    0.12
     attentive
    0.12
     gentleman
    0.12
     responsiveness
    0.12
     kindness
    0.11
     generosity
    0.11
     welcoming
    0.11
     accommodating
    0.11
     knowledgeable
    0.11
     patience
    0.11
    Activations Density 0.022%

    No Known Activations