© 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. 26268
    Prev
    Next
    INDEX
    Explanations

    question marks followed by 'are' or 'do'

    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
     Ruiz
    -0.09
     stubborn
    -0.08
    cmds
    -0.08
    Entered
    -0.08
     Claw
    -0.08
    à¹Į
    -0.08
     Entered
    -0.07
    å¿ħ
    -0.07
    366
    -0.07
     Weiss
    -0.07
    POSITIVE LOGITS
     Do
    0.19
    Do
    0.19
     Did
    0.18
     Are
    0.17
    Did
    0.17
     Want
    0.16
     did
    0.16
     Wanna
    0.16
     do
    0.16
     Does
    0.15
    Activations Density 0.047%

    No Known Activations