© 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. 33820
    Prev
    Next
    INDEX
    Explanations

    disobeying, disrespectful, defiant

    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
     obsess
    -0.09
    ewan
    -0.09
     paranoid
    -0.09
    dee
    -0.09
     genital
    -0.09
     forb
    -0.08
     torture
    -0.08
     mutil
    -0.08
     annually
    -0.08
    fal
    -0.08
    POSITIVE LOGITS
     defiance
    0.35
     disobed
    0.32
     insol
    0.32
     defiant
    0.32
     rebell
    0.31
     sass
    0.31
     disrespectful
    0.30
     disrespect
    0.29
     disob
    0.29
     rebellion
    0.27
    Activations Density 0.078%

    No Known Activations