© 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. 32089
    Prev
    Next
    INDEX
    Explanations

    like this

    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
     Bett
    -0.10
     Bild
    -0.10
     Bib
    -0.09
     unconditional
    -0.09
    utas
    -0.09
    ulls
    -0.09
     Alone
    -0.08
     petroleum
    -0.08
     Vanity
    -0.08
    olen
    -0.08
    POSITIVE LOGITS
     hovering
    0.16
     hover
    0.14
     above
    0.13
    hover
    0.12
     atop
    0.12
     towering
    0.12
     Hover
    0.11
     beside
    0.11
     looming
    0.11
     hovered
    0.11
    Activations Density 0.023%

    No Known Activations