© 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. 91146
    Prev
    Next
    INDEX
    Explanations

    in their history

    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
     ug
    -0.12
     lately
    -0.10
    ug
    -0.09
     shortly
    -0.09
     whipping
    -0.08
    yd
    -0.08
    UG
    -0.08
     Chad
    -0.08
     iss
    -0.08
    elay
    -0.08
    POSITIVE LOGITS
     entire
    0.29
     hundreds
    0.26
     thousands
    0.24
     Entire
    0.24
     entirety
    0.21
     millions
    0.20
     dozens
    0.20
     billions
    0.20
     Hundreds
    0.19
     whole
    0.18
    Activations Density 0.281%

    No Known Activations