© 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. 112429
    Prev
    Next
    INDEX
    Explanations

    generated by

    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
    -fl
    -0.12
     Moo
    -0.11
     POSIX
    -0.10
     Citadel
    -0.10
     initi
    -0.10
    cko
    -0.10
     flav
    -0.09
     fe
    -0.09
     neh
    -0.09
     Harris
    -0.09
    POSITIVE LOGITS
    enk
    0.09
    onth
    0.08
    ks
    0.08
     sisters
    0.08
     Suit
    0.08
    ym
    0.08
    net
    0.07
     Gle
    0.07
     incorporating
    0.07
    kat
    0.07
    Activations Density 0.001%

    No Known Activations