© 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. 50098
    Prev
    Next
    INDEX
    Explanations

    http or www urls

    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
    <|endoftext|>
    -0.11
    Powered
    -0.10
     bumper
    -0.10
    atcher
    -0.10
    archy
    -0.10
    mia
    -0.10
    ZF
    -0.10
    à¸ĸ
    -0.10
     nearest
    -0.09
     scratch
    -0.09
    POSITIVE LOGITS
    jon
    0.10
     Www
    0.09
     rop
    0.09
     FAQs
    0.08
    atz
    0.08
     Spir
    0.08
    <|fim_suffix|>
    0.07
     vog
    0.07
     Sta
    0.07
     stap
    0.07
    Activations Density 0.012%

    No Known Activations