© 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. 88199
    Prev
    Next
    INDEX
    Explanations

    article section headers

    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
     bead
    -0.09
    elf
    -0.09
    dana
    -0.09
    iat
    -0.08
     dilig
    -0.08
    anny
    -0.08
     cate
    -0.08
    zew
    -0.08
    MSN
    -0.08
     cowork
    -0.08
    POSITIVE LOGITS
     /(
    0.10
    ï¸
    0.10
    AZE
    0.09
    undy
    0.09
    unch
    0.09
     Seah
    0.09
     wipe
    0.09
     porno
    0.09
     upward
    0.09
    wipe
    0.09
    Activations Density 0.306%

    No Known Activations