© 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. 88684
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
     Sanchez
    -0.07
     Beginner
    -0.07
    pla
    -0.07
    pais
    -0.06
     colonization
    -0.06
     Jonas
    -0.06
     und
    -0.06
     McM
    -0.06
     kind
    -0.06
     authenticated
    -0.06
    POSITIVE LOGITS
    Ĺı
    0.16
    elay
    0.12
    itational
    0.11
    /epl
    0.11
    ·¸
    0.11
    /art
    0.11
    µ¬
    0.11
    Foot
    0.11
    ATER
    0.11
     footnote
    0.11
    Activations Density 0.001%

    No Known Activations