© 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. 90311
    Prev
    Next
    INDEX
    Explanations

    unique considerations or complexities

    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
    Better
    -0.10
     unb
    -0.10
    inz
    -0.09
     Laure
    -0.09
    idel
    -0.09
     Altern
    -0.09
     undisclosed
    -0.09
     Contemporary
    -0.09
    iet
    -0.08
     indef
    -0.08
    POSITIVE LOGITS
     unique
    0.24
     special
    0.21
     considerations
    0.21
     Unique
    0.21
    Unique
    0.20
     challenges
    0.20
     differs
    0.19
    unique
    0.19
     uniquely
    0.19
     peculiar
    0.19
    Activations Density 1.462%

    No Known Activations