© 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. 17769
    Prev
    Next
    INDEX
    Explanations

    `decided` or `ued` followed by months

    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
    AEA
    -0.11
     ðŁĴ
    -0.10
     ~>
    -0.10
    ooter
    -0.10
     ï¼
    -0.10
     prere
    -0.10
    redo
    -0.10
    drop
    -0.09
    ison
    -0.09
     gaz
    -0.09
    POSITIVE LOGITS
    <|endoftext|>
    0.10
     Outer
    0.09
     Silence
    0.08
    ...)
    0.08
     Inf
    0.08
     predic
    0.08
     twenty
    0.08
    ocol
    0.07
     sk
    0.07
    uko
    0.07
    Activations Density 0.003%

    No Known Activations