© 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. 116007
    Prev
    Next
    INDEX
    Explanations

    have / appear / serve

    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
     penchant
    -0.13
    otive
    -0.10
     Schwe
    -0.10
     Sle
    -0.10
    UPS
    -0.10
     propensity
    -0.09
    >čč↵
    -0.09
     Morton
    -0.09
    ropy
    -0.09
     tendency
    -0.09
    POSITIVE LOGITS
     be
    0.13
     Handy
    0.13
     handy
    0.13
     appear
    0.12
     emerge
    0.12
     serve
    0.11
     participate
    0.10
     accompany
    0.10
     sein
    0.10
     delivered
    0.10
    Activations Density 0.241%

    No Known Activations