© 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. 114081
    Prev
    Next
    INDEX
    Explanations

    showing details or items

    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
     bodies
    -0.12
     darkest
    -0.11
     ourselves
    -0.11
     presume
    -0.10
     oneself
    -0.10
    \:
    -0.10
    UME
    -0.10
     myself
    -0.10
    oui
    -0.09
     Bodies
    -0.09
    POSITIVE LOGITS
     despite
    0.10
     slips
    0.10
     Costume
    0.10
     costume
    0.09
     loose
    0.09
     cle
    0.09
    alo
    0.09
    subclass
    0.08
     Masc
    0.08
     gaps
    0.08
    Activations Density 0.006%

    No Known Activations