© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115179
    Prev
    Next
    INDEX
    Explanations

    writing about services or statements

    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
    ardy
    -0.09
     appet
    -0.08
     Leisure
    -0.08
     emiss
    -0.08
    adel
    -0.08
    rut
    -0.08
     highs
    -0.08
    _SN
    -0.07
     indul
    -0.07
     Judgment
    -0.07
    POSITIVE LOGITS
     shrink
    0.11
     nw
    0.11
     Bilder
    0.10
     procedure
    0.10
    pics
    0.10
     Gad
    0.10
    roe
    0.09
     Pound
    0.09
    MLS
    0.09
     pis
    0.09
    Activations Density 0.002%

    No Known Activations