© 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. 30214
    Prev
    Next
    INDEX
    Explanations

    reap harvest garner heed

    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
    l
    -0.08
     brush
    -0.08
    º«
    -0.07
     Zuk
    -0.07
     prone
    -0.07
    ipse
    -0.07
     lif
    -0.07
    roll
    -0.07
     Orden
    -0.07
    rouch
    -0.07
    POSITIVE LOGITS
    lessly
    0.18
    ful
    0.13
    less
    0.13
    lessness
    0.13
     warning
    0.13
     Cue
    0.13
     Cove
    0.12
    ance
    0.12
    LESS
    0.12
     heed
    0.12
    Activations Density 0.006%

    No Known Activations