© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 28992
    Prev
    Next
    INDEX
    Explanations

    anger, upset, or resentment

    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
     tolerated
    -0.11
    asje
    -0.11
     <<<
    -0.10
    uzu
    -0.10
     fatally
    -0.10
     Deg
    -0.10
    iser
    -0.10
    JNI
    -0.10
     Schultz
    -0.10
     unnoticed
    -0.10
    POSITIVE LOGITS
     anger
    0.31
     angry
    0.29
     resent
    0.24
     resentment
    0.23
     Angry
    0.21
     pissed
    0.20
     rage
    0.20
     furious
    0.19
     Ang
    0.17
     upset
    0.17
    Activations Density 0.084%

    No Known Activations