© 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. 31095
    Prev
    Next
    INDEX
    Explanations

    adhesion and binding components

    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
     jog
    -0.12
     shorts
    -0.12
    bard
    -0.11
     jogging
    -0.10
     stro
    -0.10
     weaving
    -0.10
     Funeral
    -0.10
     fashion
    -0.10
    ewire
    -0.10
    串
    -0.10
    POSITIVE LOGITS
     suction
    0.27
     adhesive
    0.22
     anch
    0.17
     anchors
    0.15
     anchor
    0.15
     glue
    0.15
     mounting
    0.14
     tripod
    0.14
     stability
    0.13
     sticky
    0.13
    Activations Density 0.453%

    No Known Activations