© 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. 112472
    Prev
    Next
    INDEX
    Explanations

    materials provided with

    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
    isman
    -0.11
    ither
    -0.11
    -peer
    -0.11
     demi
    -0.11
    aren
    -0.10
    inic
    -0.10
    UNG
    -0.10
     Dank
    -0.10
     Spar
    -0.10
    ARTH
    -0.10
    POSITIVE LOGITS
     Fargo
    0.08
     ribs
    0.08
     Aub
    0.08
     whichever
    0.08
    iben
    0.07
     tran
    0.07
     singled
    0.07
     lob
    0.07
    еб
    0.07
     GE
    0.07
    Activations Density 0.003%

    No Known Activations