© 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. 16642
    Prev
    Next
    INDEX
    Explanations

    supposition and assumption

    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
    dda
    -0.10
    itar
    -0.09
     bud
    -0.09
    otonin
    -0.09
     ling
    -0.09
    aset
    -0.09
    agues
    -0.09
     cro
    -0.09
    535
    -0.09
     rus
    -0.09
    POSITIVE LOGITS
    /h
    0.14
    yas
    0.09
     most
    0.09
     you
    0.09
    avad
    0.09
     Trent
    0.08
    /pop
    0.08
     pretty
    0.08
     there
    0.08
    iq
    0.08
    Activations Density 0.045%

    No Known Activations