© 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. 14464
    Prev
    Next
    INDEX
    Explanations

    appreciation and beauty

    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
    demand
    -0.11
    jin
    -0.10
     conf
    -0.10
     invitations
    -0.10
    oodles
    -0.10
     requests
    -0.10
    ç¬
    -0.10
     vaginal
    -0.10
    aba
    -0.10
    fen
    -0.10
    POSITIVE LOGITS
     appreciation
    0.14
     bodies
    0.13
     fleeting
    0.12
     appreciate
    0.12
     Apprec
    0.11
     passing
    0.11
     apprec
    0.10
     appreciated
    0.10
     encountered
    0.10
     admiration
    0.10
    Activations Density 0.039%

    No Known Activations