© 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. 113627
    Prev
    Next
    INDEX
    Explanations

    IE11, CDC.gov, employee(int), Central titles

    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
     wink
    -0.10
    erno
    -0.10
    isle
    -0.08
    LIK
    -0.08
     Kore
    -0.08
     tm
    -0.08
    avr
    -0.08
     prowess
    -0.08
     somehow
    -0.08
    wnd
    -0.08
    POSITIVE LOGITS
     embar
    0.10
     incontr
    0.10
     Join
    0.10
    ipop
    0.09
     Bass
    0.09
    coc
    0.09
     lonely
    0.09
    .Ultra
    0.09
    ,↵↵↵↵
    0.09
     geme
    0.09
    Activations Density 0.002%

    No Known Activations