© 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. 91086
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
    esser
    -0.09
    ilded
    -0.08
     diz
    -0.08
     herd
    -0.08
    LOT
    -0.08
     FileOutputStream
    -0.07
    prit
    -0.07
     liv
    -0.07
    linger
    -0.07
    lingen
    -0.07
    POSITIVE LOGITS
    -comm
    0.09
     Alter
    0.09
     Kro
    0.09
    иÑģк
    0.08
     Twe
    0.08
    <strong
    0.08
    cla
    0.08
     Harmon
    0.08
     BRE
    0.08
     hamm
    0.08
    Activations Density 0.956%

    No Known Activations