© 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. 50334
    Prev
    Next
    INDEX
    Explanations

    Mackinson, Mack Bolan, Mars, Macintosh

    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
    IZE
    -0.11
    ABLE
    -0.10
    ity
    -0.10
     conscience
    -0.10
     composing
    -0.10
    ously
    -0.09
    ered
    -0.09
     sens
    -0.09
    onus
    -0.09
     Cham
    -0.09
    POSITIVE LOGITS
    intosh
    0.13
    enzie
    0.12
    lin
    0.12
    chner
    0.11
    ificate
    0.09
     redraw
    0.09
    land
    0.09
    prot
    0.08
    len
    0.08
     dej
    0.08
    Activations Density 0.009%

    No Known Activations