© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25429
    Prev
    Next
    INDEX
    Explanations

    loop holeshooplaloop structure

    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
     praw
    -0.10
     radix
    -0.10
    NING
    -0.09
    altern
    -0.09
    azu
    -0.09
    yat
    -0.09
    acco
    -0.09
    utto
    -0.09
     Hein
    -0.09
    legt
    -0.08
    POSITIVE LOGITS
     loop
    0.19
     Loop
    0.19
     looping
    0.18
    Loop
    0.17
     loops
    0.17
    (loop
    0.17
     LOOP
    0.16
    loop
    0.16
    -loop
    0.16
    LOOP
    0.15
    Activations Density 0.020%

    No Known Activations