© 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. 17690
    Prev
    Next
    INDEX
    Explanations

    Burnham-on-Sea, Feb, », Never, If, //, See, 18, Post, âĢ¦

    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
    ollo
    -0.12
    wang
    -0.10
    :↵↵
    -0.10
    :↵
    -0.10
    :</
    -0.10
    olin
    -0.10
    :č↵
    -0.09
     fle
    -0.09
     pare
    -0.08
    kle
    -0.08
    POSITIVE LOGITS
     salv
    0.11
     relegated
    0.11
    Ljava
    0.10
     elabor
    0.10
    ziel
    0.10
    rai
    0.10
     Scr
    0.09
     bouncing
    0.09
    unden
    0.09
     Sok
    0.09
    Activations Density 0.820%

    No Known Activations