© 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. 32796
    Prev
    Next
    INDEX
    Explanations

    names following "is"

    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
     prac
    -0.08
     XK
    -0.08
     tremend
    -0.08
     lem
    -0.07
    asso
    -0.07
     rec
    -0.07
     ep
    -0.07
    -Trump
    -0.07
     Dec
    -0.07
     sett
    -0.07
    POSITIVE LOGITS
     destroyed
    0.11
    usch
    0.10
     alerted
    0.10
    master
    0.10
    lover
    0.10
    young
    0.10
     lain
    0.09
    ê¸
    0.09
    ===
    0.09
    iana
    0.09
    Activations Density 0.006%

    No Known Activations