© 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. 7190
    Prev
    Next
    INDEX
    Explanations

    attraction or interest

    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
     delivering
    -0.11
    accom
    -0.10
    ski
    -0.10
     Deliver
    -0.10
    acker
    -0.10
     rich
    -0.09
    endi
    -0.09
     homophobic
    -0.09
     doub
    -0.09
     selfish
    -0.09
    POSITIVE LOGITS
     attraction
    0.20
     attracted
    0.16
    attr
    0.15
     interest
    0.14
     attractions
    0.14
     fascination
    0.14
     aroused
    0.13
     admire
    0.12
     interested
    0.12
     grav
    0.12
    Activations Density 0.109%

    No Known Activations