© 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. 33831
    Prev
    Next
    INDEX
    Explanations

    closing quotation marks

    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
    uppe
    -0.11
    ivre
    -0.10
     dare
    -0.10
    vably
    -0.09
    essen
    -0.09
    634
    -0.09
    ='_
    -0.09
     Goods
    -0.09
    (\'
    -0.09
     embargo
    -0.09
    POSITIVE LOGITS
    âĢķ
    0.11
     âĢķ
    0.10
    —an
    0.10
     shouted
    0.09
    —I
    0.09
    ari
    0.09
    cri
    0.09
    “I
    0.09
    (CC
    0.09
    ãĢģ“
    0.09
    Activations Density 0.092%

    No Known Activations