© 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. 31130
    Prev
    Next
    INDEX
    Explanations

    rolls eyes, shake heads

    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
     brag
    -0.10
     jub
    -0.09
     boast
    -0.09
     defiant
    -0.09
     Pride
    -0.08
     celebr
    -0.08
     destabil
    -0.08
     claim
    -0.08
     malicious
    -0.08
     incons
    -0.08
    POSITIVE LOGITS
     sigh
    0.38
     sighed
    0.34
     patience
    0.28
     patiently
    0.27
     annoyed
    0.27
     frustrated
    0.25
     annoyance
    0.25
     frustration
    0.24
     impatient
    0.24
     irritation
    0.21
    Activations Density 0.121%

    No Known Activations