© 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. 88436
    Prev
    Next
    INDEX
    Explanations

    you should / can / need

    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
     expect
    -0.10
    zzo
    -0.08
     assume
    -0.08
     Pied
    -0.08
     Expect
    -0.08
     become
    -0.08
     poss
    -0.08
     Pe
    -0.08
     Station
    -0.08
     AGAIN
    -0.08
    POSITIVE LOGITS
     should
    0.20
     Should
    0.18
    should
    0.18
     ought
    0.16
    .should
    0.16
     SHOULD
    0.14
    Should
    0.14
     owe
    0.14
     deber
    0.14
     owes
    0.13
    Activations Density 0.110%

    No Known Activations