© 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. 90304
    Prev
    Next
    INDEX
    Explanations

    nothing or something

    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
     Aware
    -0.12
    aret
    -0.11
     repmat
    -0.11
    arent
    -0.11
     hopeful
    -0.10
     Bark
    -0.10
     Noticed
    -0.10
    vale
    -0.10
    inker
    -0.10
     verm
    -0.10
    POSITIVE LOGITS
     nothing
    0.40
     Nothing
    0.35
    Nothing
    0.34
    nothing
    0.32
     NOTHING
    0.29
     rien
    0.18
     nichts
    0.18
     nada
    0.18
    Few
    0.14
     few
    0.13
    Activations Density 0.132%

    No Known Activations