© 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. 6677
    Prev
    Next
    INDEX
    Explanations

    kissing and kissed actions

    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
     sarc
    -0.14
     undef
    -0.12
     lodged
    -0.12
     Visit
    -0.12
     sarcast
    -0.11
     recip
    -0.11
     loving
    -0.11
     grooming
    -0.11
    unts
    -0.10
     saf
    -0.10
    POSITIVE LOGITS
     kiss
    0.12
     passionately
    0.12
     libert
    0.11
     goodbye
    0.11
     boldly
    0.11
     kissed
    0.10
     sunset
    0.10
     electr
    0.10
     Kiss
    0.10
     outdoors
    0.10
    Activations Density 0.025%

    No Known Activations