© 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. 92001
    Prev
    Next
    INDEX
    Explanations

    wanting improvement

    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
     perm
    -0.09
    bm
    -0.09
     disrupt
    -0.09
    oir
    -0.09
    etty
    -0.09
    Inactive
    -0.09
     physic
    -0.09
    /weather
    -0.08
     procedural
    -0.08
    inerary
    -0.08
    POSITIVE LOGITS
     desired
    0.29
     desirable
    0.24
    desired
    0.23
     Desired
    0.23
     desire
    0.22
     desires
    0.20
     Desire
    0.19
     wished
    0.17
     wish
    0.16
     improvement
    0.16
    Activations Density 0.036%

    No Known Activations