© 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. 115476
    Prev
    Next
    INDEX
    Explanations

    time and time again

    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
    aget
    -0.08
    owy
    -0.08
     pity
    -0.08
    mt
    -0.08
    artz
    -0.08
    ete
    -0.08
    ffen
    -0.08
    æĹı
    -0.08
    rett
    -0.08
     cord
    -0.08
    POSITIVE LOGITS
     repeated
    0.15
     repeatedly
    0.14
     proven
    0.13
    Repeated
    0.13
     consistently
    0.12
     again
    0.12
     repetition
    0.12
     repeat
    0.12
     proved
    0.12
     repe
    0.12
    Activations Density 0.002%

    No Known Activations