© 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. 114175
    Prev
    Next
    INDEX
    Explanations

    specific separators before context

    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
    <|endoftext|>
    -0.11
     alo
    -0.10
    unte
    -0.10
     kut
    -0.09
     tou
    -0.09
     inv
    -0.09
     neh
    -0.08
    ะ
    -0.08
    statt
    -0.08
    ande
    -0.08
    POSITIVE LOGITS
    gal
    0.09
     conject
    0.09
     documented
    0.09
     unf
    0.09
     dy
    0.09
     Dy
    0.09
    eded
    0.08
     outright
    0.08
     Prepared
    0.08
    odont
    0.08
    Activations Density 0.065%

    No Known Activations