© 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. 112692
    Prev
    Next
    INDEX
    Explanations

    Rai dynasty historical figures

    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
     caster
    -0.10
    unter
    -0.10
     HK
    -0.09
     Nazi
    -0.09
     Matrix
    -0.09
    178
    -0.09
     signer
    -0.09
     harbour
    -0.09
     nineteenth
    -0.09
     Nath
    -0.09
    POSITIVE LOGITS
     Byz
    0.19
     Abbas
    0.16
     Tang
    0.15
     Arabs
    0.14
     Calif
    0.14
     Arab
    0.14
     Vikings
    0.14
     polo
    0.13
     Baghdad
    0.12
     Ansi
    0.12
    Activations Density 0.402%

    No Known Activations