© 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. 91450
    Prev
    Next
    INDEX
    Explanations

    allowed or forbidden actions

    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
     laz
    -0.09
     Stout
    -0.09
     Tin
    -0.09
     Ease
    -0.09
    uly
    -0.09
     rat
    -0.08
     bil
    -0.08
     overlook
    -0.08
     unknown
    -0.08
     Fade
    -0.08
    POSITIVE LOGITS
     forbidden
    0.53
     prohibited
    0.49
     permitted
    0.48
     allowed
    0.46
     Allowed
    0.46
     permissible
    0.43
    Allowed
    0.42
     allowable
    0.41
    allowed
    0.41
     Forbidden
    0.40
    Activations Density 1.179%

    No Known Activations