© 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. 28245
    Prev
    Next
    INDEX
    Explanations

    reference values

    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
     Accountability
    -0.11
    kir
    -0.09
     Kant
    -0.09
    imo
    -0.09
    GIS
    -0.08
    cano
    -0.08
     Pil
    -0.08
    wend
    -0.08
     irres
    -0.08
    imi
    -0.08
    POSITIVE LOGITS
     normal
    0.38
     abnormal
    0.37
     NORMAL
    0.35
     Normal
    0.34
    normal
    0.33
    Normal
    0.31
    -normal
    0.31
     normals
    0.27
     norm
    0.27
    NORMAL
    0.27
    Activations Density 0.178%

    No Known Activations