© 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. 6046
    Prev
    Next
    INDEX
    Explanations

    there is/are/have/may

    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
     most
    -0.09
     App
    -0.08
    pson
    -0.08
     relev
    -0.07
     Crow
    -0.07
    inho
    -0.07
    -tw
    -0.07
     season
    -0.07
     ë°°
    -0.07
    aal
    -0.07
    POSITIVE LOGITS
    PURE
    0.10
     repaint
    0.10
    aket
    0.10
     zun
    0.09
    nex
    0.09
     grave
    0.09
     debunk
    0.09
    811
    0.09
    lator
    0.09
    urat
    0.09
    Activations Density 0.020%

    No Known Activations