© 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. 5597
    Prev
    Next
    INDEX
    Explanations

    requesting help or suggestions

    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
     Lair
    -0.10
     Moo
    -0.10
     HOWEVER
    -0.10
     scape
    -0.10
     inherently
    -0.09
    BD
    -0.09
     unsur
    -0.09
     McCorm
    -0.09
    YES
    -0.09
     yay
    -0.09
    POSITIVE LOGITS
     please
    0.23
     Please
    0.20
    please
    0.19
     urgently
    0.19
     PLEASE
    0.19
     urgent
    0.19
    Please
    0.18
    .Please
    0.17
     Urg
    0.16
    urgent
    0.16
    Activations Density 0.652%

    No Known Activations