© 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. 17359
    Prev
    Next
    INDEX
    Explanations

    feeling states

    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
     commencement
    -0.08
     Mond
    -0.08
    uce
    -0.08
    rogen
    -0.08
    idency
    -0.07
    iant
    -0.07
     refl
    -0.07
    leur
    -0.07
     Barcl
    -0.07
    uir
    -0.07
    POSITIVE LOGITS
    less
    0.16
    ful
    0.14
    ed
    0.14
    esses
    0.13
    ally
    0.13
    ing
    0.13
    aire
    0.12
     feeling
    0.12
    dale
    0.12
    aea
    0.12
    Activations Density 0.002%

    No Known Activations