© 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. 116449
    Prev
    Next
    INDEX
    Explanations

    buried, burying, buries

    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
    wid
    -0.12
    ,strong
    -0.11
     sting
    -0.11
     sodom
    -0.11
    anges
    -0.10
     Nail
    -0.10
     flooring
    -0.10
    ofs
    -0.10
     Slee
    -0.10
     slugg
    -0.10
    POSITIVE LOGITS
     head
    0.09
    /head
    0.09
    sted
    0.09
     envelop
    0.08
     therein
    0.08
     into
    0.08
     GRAT
    0.08
     affection
    0.08
     nest
    0.08
     warmly
    0.08
    Activations Density 0.001%

    No Known Activations