© 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. 14515
    Prev
    Next
    INDEX
    Explanations

    McD, JD, Chad, WD, TD

    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
    afb
    -0.13
    bff
    -0.10
     Ronnie
    -0.10
    acb
    -0.10
    cff
    -0.10
    auss
    -0.10
     Pane
    -0.10
    oice
    -0.10
    -pane
    -0.09
    itemName
    -0.09
    POSITIVE LOGITS
     McD
    0.26
    ÙĪد
    0.25
     JD
    0.25
     Kad
    0.25
     UD
    0.25
     Chad
    0.24
     WD
    0.24
     TD
    0.24
     tad
    0.24
     KD
    0.23
    Activations Density 1.243%

    No Known Activations