© 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. 114074
    Prev
    Next
    INDEX
    Explanations

    pulling on leash

    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
    oa
    -0.07
     glo
    -0.07
    ±
    -0.07
     glowing
    -0.07
     Glo
    -0.07
    adoo
    -0.07
     deb
    -0.07
     Gregg
    -0.07
     cir
    -0.07
     blo
    -0.06
    POSITIVE LOGITS
     hairs
    0.15
    /stretch
    0.14
    -ap
    0.13
     tug
    0.12
     fibers
    0.12
     strings
    0.12
     stretches
    0.12
     Stretch
    0.12
     stretching
    0.12
     Fra
    0.12
    Activations Density 0.024%

    No Known Activations