© 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. 88206
    Prev
    Next
    INDEX
    Explanations

    of her / his / the

    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
     voluntarily
    -0.12
    clus
    -0.11
     volunteers
    -0.11
    enu
    -0.11
    dar
    -0.10
     signals
    -0.10
     Pruitt
    -0.10
    quin
    -0.10
    opr
    -0.10
     hug
    -0.10
    POSITIVE LOGITS
     notebook
    0.09
    ests
    0.08
    -stage
    0.08
    -enter
    0.08
     thro
    0.07
    GMT
    0.07
     RT
    0.07
     amusement
    0.07
     tents
    0.07
    essel
    0.07
    Activations Density 0.019%

    No Known Activations