© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49796
    Prev
    Next
    INDEX
    Explanations

    if you

    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
     Emmanuel
    -0.09
     luc
    -0.09
    EVENT
    -0.09
    æ£
    -0.09
    amus
    -0.09
     Eck
    -0.09
     Voor
    -0.08
    hq
    -0.08
    andy
    -0.08
    lbrace
    -0.08
    POSITIVE LOGITS
     any
    0.14
     anybody
    0.14
     anyhow
    0.13
    ä»»
    0.12
    any
    0.11
    Any
    0.11
     anyone
    0.11
     Any
    0.11
    .sul
    0.10
     Profession
    0.09
    Activations Density 0.127%

    No Known Activations