© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115135
    Prev
    Next
    INDEX
    Explanations

    attachment and bonding

    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
     intersect
    -0.10
     spokes
    -0.10
     entertainment
    -0.10
    asl
    -0.10
     wast
    -0.09
     SIN
    -0.09
     intersects
    -0.09
     rect
    -0.09
     intersections
    -0.09
     turf
    -0.09
    POSITIVE LOGITS
     oxy
    0.31
     bonding
    0.28
     cudd
    0.24
     bond
    0.24
     Attachment
    0.23
     attachment
    0.22
     bonded
    0.22
    bond
    0.20
     bonds
    0.19
     hugs
    0.19
    Activations Density 0.221%

    No Known Activations