© 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. 29225
    Prev
    Next
    INDEX
    Explanations

    unintentionally, unknowingly, inadvertently

    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
    udas
    -0.11
     Binder
    -0.11
     Kee
    -0.10
    feld
    -0.09
    epy
    -0.09
     Fant
    -0.09
    apons
    -0.09
    844
    -0.08
     Rab
    -0.08
    nic
    -0.08
    POSITIVE LOGITS
     unintention
    0.66
     unwitting
    0.61
     unknow
    0.57
     inadvert
    0.53
     inadvertently
    0.52
     unconscious
    0.48
     unintended
    0.45
     uncon
    0.42
     consciously
    0.42
     unaware
    0.40
    Activations Density 0.181%

    No Known Activations