© 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. 115008
    Prev
    Next
    INDEX
    Explanations

    modes and options

    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
    -none
    -0.12
     Bauer
    -0.11
     exagger
    -0.10
    lld
    -0.10
    OLA
    -0.10
    IELDS
    -0.10
    ropa
    -0.10
    Arrow
    -0.10
    elib
    -0.10
     SUCH
    -0.10
    POSITIVE LOGITS
     whichever
    0.15
     modes
    0.14
     convenience
    0.12
     wherever
    0.12
     mode
    0.12
     flexibility
    0.12
     options
    0.11
     Modes
    0.11
     convenient
    0.11
     respectively
    0.11
    Activations Density 0.200%

    No Known Activations