© 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. 31971
    Prev
    Next
    INDEX
    Explanations

    ur.com

    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
     Fla
    -0.10
    crawl
    -0.09
    uries
    -0.08
     Cam
    -0.08
    IOD
    -0.08
    Grace
    -0.08
    LBL
    -0.07
     unarmed
    -0.07
     Daddy
    -0.07
     unb
    -0.07
    POSITIVE LOGITS
     regist
    0.13
     Emil
    0.11
     Receipt
    0.11
     Gors
    0.11
    essel
    0.10
     optimistic
    0.10
     Nigel
    0.10
     Epstein
    0.10
     rec
    0.10
    chan
    0.10
    Activations Density 0.001%

    No Known Activations