© 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. 17731
    Prev
    Next
    INDEX
    Explanations

    especially considering, since, if, after

    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
    owe
    -0.10
     Suff
    -0.10
    éĻ¤
    -0.10
     suff
    -0.10
    (QL
    -0.10
     either
    -0.10
     suf
    -0.10
    Few
    -0.10
     Suppose
    -0.09
    ub
    -0.09
    POSITIVE LOGITS
     since
    0.25
     considering
    0.21
    since
    0.19
    Since
    0.16
     Since
    0.16
     given
    0.15
     Considering
    0.15
    Considering
    0.13
     knowing
    0.12
    given
    0.12
    Activations Density 0.027%

    No Known Activations