© 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. 114487
    Prev
    Next
    INDEX
    Explanations

    see + what/anything/it

    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
    rawer
    -0.10
     Duncan
    -0.10
    cott
    -0.10
    quan
    -0.10
    adesh
    -0.10
    strom
    -0.09
    adt
    -0.09
    pers
    -0.09
    liable
    -0.09
     flavored
    -0.09
    POSITIVE LOGITS
     clearly
    0.18
     across
    0.14
     Clearly
    0.13
     poorly
    0.12
    Clearly
    0.12
     inside
    0.11
     CLEAR
    0.11
     into
    0.11
     through
    0.10
    -clear
    0.10
    Activations Density 0.057%

    No Known Activations