© 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. 115052
    Prev
    Next
    INDEX
    Explanations

    REG word stems

    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
    heets
    -0.09
     Winn
    -0.09
     mysterious
    -0.08
     declar
    -0.08
    ape
    -0.08
    yg
    -0.08
    age
    -0.08
    à¹Į
    -0.08
     uso
    -0.08
    eri
    -0.08
    POSITIVE LOGITS
    roup
    0.14
    gae
    0.14
    .MustCompile
    0.14
    ulated
    0.13
    arded
    0.13
    enerative
    0.12
    ión
    0.12
    ISTRATION
    0.12
    ional
    0.12
    icide
    0.12
    Activations Density 0.216%

    No Known Activations