© 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. 113648
    Prev
    Next
    INDEX
    Explanations

    time stamps AM/PM

    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
    ace
    -0.10
    POP
    -0.09
     minus
    -0.09
    Storm
    -0.09
     interference
    -0.09
    cover
    -0.09
     domina
    -0.09
    htag
    -0.09
    Minus
    -0.08
    -minus
    -0.08
    POSITIVE LOGITS
    ASM
    0.10
     Wh
    0.10
     mid
    0.09
     unst
    0.09
     push
    0.09
     Clem
    0.09
    guarded
    0.09
    ess
    0.08
    ulla
    0.08
    -push
    0.08
    Activations Density 0.151%

    No Known Activations