© 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. 6238
    Prev
    Next
    INDEX
    Explanations

    Did you know

    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
     arrog
    -0.08
    lbrace
    -0.08
    (LL
    -0.08
     âĢķ
    -0.07
    [R
    -0.07
     adidas
    -0.07
     imageURL
    -0.07
     näch
    -0.07
    (JS
    -0.07
     yuan
    -0.07
    POSITIVE LOGITS
    etCode
    0.10
     Bbw
    0.10
    \System
    0.10
     Seks
    0.09
     Enlightenment
    0.09
     WHATSOEVER
    0.09
     INCLUDED
    0.09
    .Xr
    0.09
     Sexe
    0.09
     PARTICULAR
    0.09
    Activations Density 3.725%

    No Known Activations