© 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. 115324
    Prev
    Next
    INDEX
    Explanations

    how, what, if

    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
     today
    -0.20
     currently
    -0.20
     tonight
    -0.19
     your
    -0.17
     nowadays
    -0.17
    your
    -0.17
     presently
    -0.16
     yourself
    -0.16
    currently
    -0.16
     Currently
    -0.15
    POSITIVE LOGITS
     myself
    0.20
     hadn
    0.18
     seemed
    0.18
     my
    0.18
    æĪijçļĦ
    0.16
     had
    0.15
     habÃŃa
    0.14
    my
    0.14
     wasn
    0.14
     avait
    0.13
    Activations Density 0.975%

    No Known Activations