© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48568
    Prev
    Next
    INDEX
    Explanations

    after was, be, by, of, Code, :

    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
     hobby
    -0.11
    irc
    -0.11
    Disc
    -0.11
     Spar
    -0.11
    ertz
    -0.10
     Discrim
    -0.10
    doll
    -0.10
     Turtle
    -0.10
    adm
    -0.10
     misd
    -0.10
    POSITIVE LOGITS
     inn
    0.08
     lyn
    0.07
     brav
    0.07
     locals
    0.07
     corner
    0.07
     molds
    0.07
     Stuff
    0.07
     lex
    0.07
     flea
    0.07
     Jeans
    0.06
    Activations Density 0.003%

    No Known Activations