© 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. 113778
    Prev
    Next
    INDEX
    Explanations

    Blink and Berlin

    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
    roz
    -0.10
    ICO
    -0.10
    osen
    -0.09
    malink
    -0.09
    ftime
    -0.09
    dpi
    -0.09
    avin
    -0.08
    Feels
    -0.08
    ainty
    -0.08
     Eag
    -0.08
    POSITIVE LOGITS
     blink
    0.14
    er
    0.12
    -eyed
    0.10
    ered
    0.10
     caret
    0.10
     eye
    0.09
    çľ
    0.09
     Blink
    0.09
     eyel
    0.09
    orphic
    0.09
    Activations Density 0.009%

    No Known Activations