© 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. 15204
    Prev
    Next
    INDEX
    Explanations

    immediately saw

    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
     kisses
    -0.24
     kissing
    -0.24
     kiss
    -0.23
     kissed
    -0.23
     Kiss
    -0.17
     hugs
    -0.15
     cudd
    -0.15
     hugged
    -0.14
     handshake
    -0.14
     hug
    -0.13
    POSITIVE LOGITS
     beck
    0.13
     masturbating
    0.13
     watched
    0.12
    -wall
    0.12
     masturb
    0.11
     provoc
    0.11
     WATCH
    0.11
     yell
    0.11
    .dialog
    0.11
    uci
    0.10
    Activations Density 0.054%

    No Known Activations