© 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. 4859
    Prev
    Next
    INDEX
    Explanations

    nick or nickel

    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
    educt
    -0.08
     Jed
    -0.08
     Quar
    -0.08
     tapi
    -0.08
    Īĺ
    -0.08
     shr
    -0.08
     Leia
    -0.08
    RX
    -0.08
     hitch
    -0.07
     Shoe
    -0.07
    POSITIVE LOGITS
     Nick
    0.17
    Nick
    0.15
    .nick
    0.14
     nick
    0.13
     Nichols
    0.13
     Nickel
    0.12
    Nich
    0.11
     NIC
    0.11
     UIP
    0.10
     nickel
    0.10
    Activations Density 0.107%

    No Known Activations