© 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. 5528
    Prev
    Next
    INDEX
    Explanations

    default context

    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
     secular
    -0.12
     conting
    -0.12
    lbrace
    -0.11
    sec
    -0.11
     sek
    -0.10
     Nev
    -0.10
    ìĥģ
    -0.10
     Lond
    -0.10
     Continent
    -0.10
    bak
    -0.10
    POSITIVE LOGITS
     stre
    0.08
     unic
    0.07
     jou
    0.07
    tp
    0.07
    /as
    0.07
    /tcp
    0.07
     Registers
    0.07
     tol
    0.07
     grop
    0.07
     editable
    0.07
    Activations Density 0.021%

    No Known Activations