© 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. 90437
    Prev
    Next
    INDEX
    Explanations

    you/me and the next word

    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
     reassuring
    -0.08
    fh
    -0.08
     hast
    -0.07
    ochen
    -0.07
     cling
    -0.07
     Ready
    -0.07
     vain
    -0.07
    enen
    -0.07
     Peek
    -0.07
    ock
    -0.06
    POSITIVE LOGITS
     fooled
    0.15
    peg
    0.14
     outnumber
    0.13
     peg
    0.12
    lei
    0.12
     trapped
    0.12
    imit
    0.12
    ,tr
    0.11
    enberg
    0.11
    Titles
    0.11
    Activations Density 0.014%

    No Known Activations