© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 5839
    Prev
    Next
    INDEX
    Explanations

    urls and quotation marks

    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
     Fay
    -0.09
    ...)↵↵
    -0.09
    ...)
    -0.08
    raq
    -0.08
    ...)↵
    -0.08
     -↵
    -0.08
     pointing
    -0.08
     pac
    -0.08
     paralyzed
    -0.08
    )?↵
    -0.08
    POSITIVE LOGITS
    Hello
    0.12
    Attention
    0.11
     Damn
    0.11
     intervening
    0.11
     foolish
    0.11
     damned
    0.11
    Damn
    0.11
    aris
    0.10
     Heads
    0.10
    Ps
    0.10
    Activations Density 0.017%

    No Known Activations