© 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. 33110
    Prev
    Next
    INDEX
    Explanations

    without regrets, without tests, without restrictions, without government

    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
     pudd
    -0.09
     unfamiliar
    -0.08
     Unknown
    -0.08
     acidic
    -0.08
    arak
    -0.08
     poly
    -0.08
     quiz
    -0.07
     drastic
    -0.07
    ewe
    -0.07
    ajor
    -0.07
    POSITIVE LOGITS
     constraints
    0.34
     restraint
    0.33
     restrictions
    0.33
     constraint
    0.29
     restrained
    0.29
     restriction
    0.28
     Restrictions
    0.26
     Constraints
    0.26
     restrain
    0.26
     constrain
    0.25
    Activations Density 0.181%

    No Known Activations