© 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. 50101
    Prev
    Next
    INDEX
    Explanations

    title of a report or study

    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
     –
    -0.12
    Essay
    -0.11
     (“
    -0.10
    ftar
    -0.10
     (**
    -0.10
     “âĢ¦
    -0.10
    (`
    -0.10
    htag
    -0.10
    INDEX
    -0.10
    -badge
    -0.09
    POSITIVE LOGITS
    :;↵
    0.09
     Sche
    0.08
     âĢİ
    0.08
                                                ↵
    0.07
    [:]↵
    0.07
     Bir
    0.07
    č↵↵
    0.07
    ï¸
    0.07
    */,↵
    0.07
     Linden
    0.07
    Activations Density 3.028%

    No Known Activations