© 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. 15073
    Prev
    Next
    INDEX
    Explanations

    listen up

    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
     dreadful
    -0.17
     lovely
    -0.17
     wonderful
    -0.15
     darling
    -0.15
     delightful
    -0.15
     dear
    -0.14
     Lovely
    -0.14
     quite
    -0.14
     wonderfully
    -0.13
     Wonderful
    -0.13
    POSITIVE LOGITS
     dude
    0.38
     Dude
    0.34
     dudes
    0.34
     fucking
    0.25
     shit
    0.25
     fuck
    0.25
     awesome
    0.23
     Yeah
    0.23
     yeah
    0.23
     fucked
    0.22
    Activations Density 0.227%

    No Known Activations