© 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. 32929
    Prev
    Next
    INDEX
    Explanations

    relates to location or state of being

    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
    eba
    -0.11
    utz
    -0.10
     zer
    -0.10
    rq
    -0.10
     Hon
    -0.10
    ivre
    -0.09
    gw
    -0.09
     Kauf
    -0.09
     Poz
    -0.09
    arty
    -0.09
    POSITIVE LOGITS
     belonged
    0.28
     belongs
    0.28
     belong
    0.27
     represents
    0.25
     corresponds
    0.25
     represent
    0.24
     correspond
    0.21
     relates
    0.20
     originates
    0.19
     stemmed
    0.19
    Activations Density 0.584%

    No Known Activations