© 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. 88809
    Prev
    Next
    INDEX
    Explanations

    patterns and structure

    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
     priced
    -0.09
    -priced
    -0.08
    LER
    -0.08
    -aligned
    -0.08
    -required
    -0.08
    -built
    -0.08
     unb
    -0.08
     Loren
    -0.07
    _specific
    -0.07
     Excellence
    -0.07
    POSITIVE LOGITS
     structure
    0.23
     sizes
    0.22
     levels
    0.22
     status
    0.22
     size
    0.21
     styles
    0.21
     level
    0.20
     patterns
    0.20
     characteristics
    0.20
     demographics
    0.20
    Activations Density 1.990%

    No Known Activations