© 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. 7527
    Prev
    Next
    INDEX
    Explanations

    outfits for Guys

    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
    .ll
    -0.12
    nore
    -0.12
     Paw
    -0.11
     bere
    -0.11
     Exhibit
    -0.11
    è±
    -0.10
    Surname
    -0.10
    ere
    -0.10
    (Optional
    -0.10
     mog
    -0.10
    POSITIVE LOGITS
     Ingram
    0.07
     Cree
    0.07
     Drill
    0.06
    laps
    0.06
     Cup
    0.06
     invis
    0.06
     Golf
    0.06
     Queen
    0.06
    sex
    0.06
     indirectly
    0.06
    Activations Density 0.023%

    No Known Activations