© 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. 88541
    Prev
    Next
    INDEX
    Explanations

    complaining or questioning someone

    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
     #-
    -0.10
     stead
    -0.10
     cle
    -0.09
    Poss
    -0.09
     [@
    -0.09
     priv
    -0.09
    ACY
    -0.09
     unpredictable
    -0.09
     Reyes
    -0.09
     Wikipedia
    -0.09
    POSITIVE LOGITS
     complaining
    0.28
     lament
    0.28
     complain
    0.25
     complains
    0.23
     complaints
    0.22
     complained
    0.22
     complaint
    0.21
     brag
    0.19
     Complaint
    0.17
     plaint
    0.17
    Activations Density 0.198%

    No Known Activations