© 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. 89303
    Prev
    Next
    INDEX
    Explanations

    speaker said

    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
     Bre
    -0.09
     bre
    -0.09
     specifier
    -0.08
     emphas
    -0.08
     ;)
    -0.07
     Duffy
    -0.07
    inton
    -0.07
     Mori
    -0.07
     emphasizing
    -0.07
     Helm
    -0.07
    POSITIVE LOGITS
    isse
    0.12
    izi
    0.11
    enga
    0.11
    anja
    0.11
    engu
    0.11
    Īëĭ¤
    0.11
     ink
    0.10
     tack
    0.10
    edo
    0.10
     initially
    0.10
    Activations Density 0.024%

    No Known Activations