© 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. 47869
    Prev
    Next
    INDEX
    Explanations

    success, luck, research, help

    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
     acc
    -0.09
    endor
    -0.08
     meetings
    -0.08
     fore
    -0.08
     staring
    -0.08
     revolution
    -0.08
    occo
    -0.08
     indie
    -0.08
    gallery
    -0.08
     Attr
    -0.08
    POSITIVE LOGITS
    iju
    0.11
    Fee
    0.09
    ardo
    0.09
     dues
    0.09
     asym
    0.09
    idences
    0.09
    ãģĤãĤĬãģĮãģ¨ãģĨãģĶãģĸ
    0.09
     Inspector
    0.09
    ingu
    0.09
     reminiscent
    0.09
    Activations Density 0.001%

    No Known Activations