© 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. 113233
    Prev
    Next
    INDEX
    Explanations

    special characters enclosing words

    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
    s
    -0.12
    esion
    -0.12
    ed
    -0.12
    al
    -0.10
    ly
    -0.09
    esium
    -0.09
    acias
    -0.09
    o
    -0.09
    ########
    -0.09
    ÑĤÑĮ
    -0.09
    POSITIVE LOGITS
    ¸
    0.12
    urer
    0.11
    ico
    0.11
    ienne
    0.10
    oria
    0.10
     Wilkinson
    0.10
     amore
    0.10
    ually
    0.09
    uer
    0.09
     succeeding
    0.09
    Activations Density 0.005%

    No Known Activations