© 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. 15872
    Prev
    Next
    INDEX
    Explanations

    .

    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
     rdr
    -0.07
     cert
    -0.07
     Gund
    -0.06
     Pic
    -0.06
     tou
    -0.06
     uncon
    -0.06
     Feather
    -0.06
    xyz
    -0.06
     stew
    -0.06
     uns
    -0.06
    POSITIVE LOGITS
    /X
    0.25
     getX
    0.22
     NX
    0.21
     SX
    0.20
     MX
    0.20
     SAX
    0.20
    pyx
    0.20
    ,X
    0.19
    AXB
    0.19
     LX
    0.19
    Activations Density 2.855%

    No Known Activations