© 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. 115674
    Prev
    Next
    INDEX
    Explanations

    expressing feelings to others

    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
     my
    -0.10
     neur
    -0.09
     prompting
    -0.09
    gain
    -0.09
     habit
    -0.09
     subconscious
    -0.09
     Salem
    -0.09
     Braun
    -0.09
    513
    -0.09
     unconscious
    -0.09
    POSITIVE LOGITS
     Apprec
    0.13
     apprec
    0.12
     appreciate
    0.11
     available
    0.11
     appreciation
    0.10
     condolences
    0.10
     thanks
    0.10
     disple
    0.10
    available
    0.10
     vant
    0.10
    Activations Density 0.030%

    No Known Activations