© 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. 4656
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming constructs

    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
     Couple
    -0.07
     imp
    -0.06
     rep
    -0.06
     Estr
    -0.06
     Mos
    -0.06
    xt
    -0.06
     Kend
    -0.06
     mil
    -0.06
    áŁĴáŀ
    -0.06
     ausp
    -0.06
    POSITIVE LOGITS
    <dd
    0.11
    (skip
    0.11
    ErrorException
    0.11
     Davies
    0.10
    =Value
    0.10
    [op
    0.09
     cref
    0.09
    请éĢīæĭ©
    0.09
     uns
    0.09
    meld
    0.09
    Activations Density 1.178%

    No Known Activations