© 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. 90394
    Prev
    Next
    INDEX
    Explanations

    separators and decorative lines

    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
     definit
    -0.09
    _Bool
    -0.08
     sque
    -0.08
    Enlarge
    -0.08
     bare
    -0.08
     disg
    -0.08
    alia
    -0.08
    Alive
    -0.08
    ĸī
    -0.08
     loose
    -0.08
    POSITIVE LOGITS
    ITT
    0.11
    ---</
    0.10
    WEEN
    0.10
    âĶĢ
    0.10
    oner
    0.09
     Curtain
    0.09
    ––
    0.09
    took
    0.09
    ——
    0.09
    ê²½
    0.08
    Activations Density 0.112%

    No Known Activations