© 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. 88122
    Prev
    Next
    INDEX
    Explanations

    became known or popular

    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
     former
    -0.11
    SHOT
    -0.10
    former
    -0.10
     currently
    -0.10
     talents
    -0.09
    rama
    -0.09
    üz
    -0.09
    AssignableFrom
    -0.09
    kan
    -0.09
    ehr
    -0.09
    POSITIVE LOGITS
     overnight
    0.15
     disillusion
    0.12
     obsessed
    0.12
     popular
    0.11
     famous
    0.11
     Overnight
    0.11
     infamous
    0.11
     thereafter
    0.11
     instant
    0.11
     sensation
    0.11
    Activations Density 0.088%

    No Known Activations