© 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. 15647
    Prev
    Next
    INDEX
    Explanations

    information withholding

    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
    empo
    -0.11
     Cah
    -0.11
     anonymous
    -0.10
     cleansing
    -0.10
     Tit
    -0.10
    bookmark
    -0.10
     Bold
    -0.10
    etter
    -0.10
     vit
    -0.10
    -pos
    -0.10
    POSITIVE LOGITS
     divul
    0.16
     details
    0.16
     disclose
    0.15
     disclosing
    0.15
     detailed
    0.14
     Details
    0.13
     specifics
    0.13
     disclosure
    0.12
    details
    0.12
     detal
    0.12
    Activations Density 0.082%

    No Known Activations