© 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. 29223
    Prev
    Next
    INDEX
    Explanations

    hang over, hang out, hangouts

    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
    er
    -0.13
    ed
    -0.12
    quent
    -0.10
    eer
    -0.10
    cek
    -0.10
    ingen
    -0.10
    lys
    -0.09
    erca
    -0.09
    ing
    -0.09
    odic
    -0.09
    POSITIVE LOGITS
     hang
    0.16
    outs
    0.15
    over
    0.15
    out
    0.14
    overs
    0.13
     Hang
    0.12
    xiety
    0.12
    zhou
    0.11
     ups
    0.11
    hang
    0.10
    Activations Density 0.006%

    No Known Activations