© 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. 5719
    Prev
    Next
    INDEX
    Explanations

    cutting and sharp tools

    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
    /sm
    -0.09
    tober
    -0.09
     Lucky
    -0.08
     shovel
    -0.08
     whistle
    -0.08
     unlucky
    -0.08
    /off
    -0.08
     Cran
    -0.07
    otes
    -0.07
     CrossRef
    -0.07
    POSITIVE LOGITS
     opener
    0.12
    kop
    0.12
    -shaped
    0.11
    iosa
    0.11
    lift
    0.10
     shut
    0.10
     clipping
    0.10
    wort
    0.10
     clipped
    0.10
    aurus
    0.10
    Activations Density 0.004%

    No Known Activations