© 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. 5786
    Prev
    Next
    INDEX
    Explanations

    appearance and looks

    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
    sto
    -0.08
     fut
    -0.08
     fascinating
    -0.08
     impl
    -0.08
     initially
    -0.08
     amazing
    -0.08
    hed
    -0.08
    alian
    -0.07
    /Page
    -0.07
     unbelievable
    -0.07
    POSITIVE LOGITS
     pride
    0.22
     boast
    0.20
     proud
    0.20
     boasted
    0.17
     confident
    0.17
     boasting
    0.17
     Pride
    0.17
     self
    0.17
     confidence
    0.17
     proudly
    0.16
    Activations Density 0.033%

    No Known Activations