© 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. 117085
    Prev
    Next
    INDEX
    Explanations

    fantasy literature titles

    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
     Peach
    -0.12
     libertin
    -0.12
     Giul
    -0.12
     Dickens
    -0.11
     Watt
    -0.11
     Junk
    -0.11
     American
    -0.11
    /op
    -0.11
     libertine
    -0.11
     clown
    -0.11
    POSITIVE LOGITS
     lorem
    0.18
     Tolkien
    0.17
     Sind
    0.16
     Elves
    0.15
     Morg
    0.15
     Lorem
    0.14
     Orc
    0.13
     elves
    0.13
     realms
    0.13
     orc
    0.12
    Activations Density 0.156%

    No Known Activations