© 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. 46827
    Prev
    Next
    INDEX
    Explanations

    person roles

    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
     cac
    -0.13
    OF
    -0.10
     clam
    -0.09
    Trait
    -0.09
     overrun
    -0.09
     aloud
    -0.09
     contested
    -0.09
     invis
    -0.09
     impe
    -0.09
     besie
    -0.09
    POSITIVE LOGITS
     smile
    0.11
     wink
    0.11
     smiling
    0.10
     hesitate
    0.10
    yer
    0.10
     Wick
    0.10
     consulting
    0.09
     lips
    0.09
     glance
    0.09
     carefully
    0.09
    Activations Density 0.014%

    No Known Activations