© 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. 33629
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code comments

    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
     unarmed
    -0.12
    usters
    -0.12
    ilenames
    -0.11
    âĢİ
    -0.11
    NES
    -0.11
     fal
    -0.10
    ala
    -0.10
    keys
    -0.10
    ReadWrite
    -0.10
     bes
    -0.10
    POSITIVE LOGITS
    âĢ¦)↵↵
    0.10
    ulado
    0.09
     Coff
    0.07
     ORD
    0.07
     RTE
    0.07
    itized
    0.07
    ĥĿ
    0.06
    !!)↵
    0.06
     provid
    0.06
    uf
    0.06
    Activations Density 0.108%

    No Known Activations