© 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. 113786
    Prev
    Next
    INDEX
    Explanations

    canvas rendering context

    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
    zed
    -0.11
    ofil
    -0.09
    otic
    -0.09
     Bam
    -0.09
    legate
    -0.09
    ãģĹãģŁ
    -0.09
     granite
    -0.09
     Frag
    -0.09
     Webcam
    -0.09
     wig
    -0.08
    POSITIVE LOGITS
    RenderingContext
    0.15
     canvas
    0.13
     bag
    0.12
    leo
    0.12
    .Canvas
    0.12
     canv
    0.12
     painting
    0.12
     GFX
    0.11
     painters
    0.11
     painter
    0.10
    Activations Density 0.017%

    No Known Activations