© 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. 25995
    Prev
    Next
    INDEX
    Explanations

    belief and doubt

    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
    ed
    -0.10
    dio
    -0.09
    yd
    -0.09
    yb
    -0.09
    ling
    -0.09
    empl
    -0.09
    etto
    -0.09
    unds
    -0.09
     disposition
    -0.08
    ded
    -0.08
    POSITIVE LOGITS
    vably
    0.21
    vable
    0.17
    ving
    0.14
    vely
    0.13
     unbelievable
    0.12
    anford
    0.12
     disbelief
    0.11
     incred
    0.11
    bow
    0.11
     freaking
    0.11
    Activations Density 0.003%

    No Known Activations