© 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. 113375
    Prev
    Next
    INDEX
    Explanations

    stretches and supported

    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
     lov
    -0.13
    taire
    -0.11
     untranslated
    -0.10
     improvised
    -0.10
     Hund
    -0.10
    951
    -0.10
    ê·
    -0.10
     Fasc
    -0.09
     purs
    -0.09
    usty
    -0.09
    POSITIVE LOGITS
     spread
    0.11
     nude
    0.11
     naked
    0.10
     stret
    0.09
     Machines
    0.09
     strapped
    0.09
     toast
    0.09
     buff
    0.09
    spread
    0.09
     quad
    0.09
    Activations Density 0.005%

    No Known Activations