© 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. 26227
    Prev
    Next
    INDEX
    Explanations

    Sherlock Holmes

    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
     Salvador
    -0.10
     Laguna
    -0.10
     Dallas
    -0.10
     Dez
    -0.10
     Gaines
    -0.09
     Kota
    -0.09
     Diablo
    -0.09
     Braves
    -0.09
     nad
    -0.08
     Palm
    -0.08
    POSITIVE LOGITS
     Sherlock
    0.37
     Watson
    0.27
     Holmes
    0.26
     Mori
    0.24
     Conan
    0.21
    Wat
    0.19
     deductions
    0.17
    Sher
    0.17
     deduction
    0.16
     Detective
    0.15
    Activations Density 0.064%

    No Known Activations