© 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. 31187
    Prev
    Next
    INDEX
    Explanations

    after linking word

    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
     pimp
    -0.09
     Briggs
    -0.08
     Terror
    -0.07
     grooming
    -0.07
     Judge
    -0.07
     CORS
    -0.06
     prere
    -0.06
    omentum
    -0.06
    apel
    -0.06
    #pragma
    -0.06
    POSITIVE LOGITS
    etch
    0.13
     dew
    0.12
     lil
    0.11
     worn
    0.11
     Anatomy
    0.11
    ertos
    0.11
     wearing
    0.10
     Dew
    0.10
     lassen
    0.10
    /Library
    0.10
    Activations Density 0.106%

    No Known Activations