© 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. 4163
    Prev
    Next
    INDEX
    Explanations

    tease teaser tantalizing

    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
     spontaneously
    -0.09
     forged
    -0.09
    onda
    -0.08
     permanently
    -0.08
    907
    -0.08
     requested
    -0.08
     cleanly
    -0.08
     definit
    -0.07
     cont
    -0.07
    requested
    -0.07
    POSITIVE LOGITS
     tease
    0.23
     tantal
    0.20
     teased
    0.20
     teasing
    0.17
     teaser
    0.15
     teas
    0.14
     merciless
    0.14
     bait
    0.14
     nipples
    0.13
     endlessly
    0.13
    Activations Density 0.013%

    No Known Activations