© 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. 113097
    Prev
    Next
    INDEX
    Explanations

    informed by authors

    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
     thru
    -0.13
     "...
    -0.13
     “âĢ¦
    -0.13
     detr
    -0.11
     foc
    -0.11
     amongst
    -0.10
     oft
    -0.10
     Dich
    -0.10
    (tm
    -0.10
     whilst
    -0.10
    POSITIVE LOGITS
     echt
    0.17
     ÂŃ
    0.16
     arriv
    0.14
     famously
    0.14
     duly
    0.13
     precisely
    0.13
    .''
    0.13
     él
    0.13
     Slate
    0.13
     dispatch
    0.12
    Activations Density 0.663%

    No Known Activations