© 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. 26684
    Prev
    Next
    INDEX
    Explanations

    questions or exclamations followed by sentences

    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
     rival
    -0.11
     breathing
    -0.10
    ushed
    -0.10
     scratching
    -0.10
     Prairie
    -0.10
     pÅĤ
    -0.10
     shooting
    -0.10
     MUCH
    -0.09
    Cheers
    -0.09
    aten
    -0.09
    POSITIVE LOGITS
    dit
    0.09
     embr
    0.09
     mob
    0.09
     search
    0.08
     Found
    0.08
     cis
    0.08
     uncover
    0.08
     Vulcan
    0.07
     promot
    0.07
    ,map
    0.07
    Activations Density 0.002%

    No Known Activations