© 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. 114037
    Prev
    Next
    INDEX
    Explanations

    numbers after dates or codes

    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
     verm
    -0.09
    licher
    -0.09
     retros
    -0.09
     får
    -0.09
     gradu
    -0.09
    CLICK
    -0.09
     probe
    -0.09
    ,strong
    -0.09
     allo
    -0.09
    ï¸ı
    -0.09
    POSITIVE LOGITS
     upside
    0.09
    osi
    0.09
     convention
    0.09
     TOD
    0.08
    irit
    0.08
     last
    0.08
     inverted
    0.08
     fav
    0.08
    dl
    0.08
     absurd
    0.08
    Activations Density 0.001%

    No Known Activations