© 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. 16107
    Prev
    Next
    INDEX
    Explanations

    image contrast

    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
    kir
    -0.10
     invitations
    -0.10
     conversations
    -0.10
     datap
    -0.10
     discussions
    -0.10
    dek
    -0.09
    venge
    -0.09
    eva
    -0.09
     invitation
    -0.09
    proof
    -0.09
    POSITIVE LOGITS
     atleast
    0.08
     colourful
    0.07
     Span
    0.07
     bzw
    0.07
     Silk
    0.07
    Span
    0.07
     /^\
    0.07
     seulement
    0.07
     tua
    0.07
    Scaled
    0.07
    Activations Density 3.744%

    No Known Activations