© 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. 33667
    Prev
    Next
    INDEX
    Explanations

    attraction compatibility liking

    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
     Abr
    -0.11
     fears
    -0.11
     accus
    -0.11
     Mine
    -0.10
     sensitive
    -0.10
     Unused
    -0.10
     understands
    -0.10
     accusation
    -0.10
     accusations
    -0.10
     delicate
    -0.09
    POSITIVE LOGITS
     attraction
    0.20
     attracted
    0.16
     compatibility
    0.15
    Attr
    0.15
     Compatibility
    0.14
     romant
    0.14
     liking
    0.14
    compat
    0.14
     attractions
    0.14
     criterion
    0.13
    Activations Density 0.036%

    No Known Activations