© 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. 7098
    Prev
    Next
    INDEX
    Explanations

    legal/official actions taken

    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
     undergo
    -0.16
     underwent
    -0.16
     undergoing
    -0.14
     undergone
    -0.12
     Borrow
    -0.10
     boyc
    -0.10
     Volunteer
    -0.10
     opting
    -0.10
     voluntarily
    -0.10
     volunteer
    -0.10
    POSITIVE LOGITS
     penal
    0.17
     cater
    0.15
     accommodating
    0.15
     refund
    0.14
     assign
    0.14
     award
    0.14
     refunded
    0.13
     administr
    0.13
     accommod
    0.13
     recommend
    0.13
    Activations Density 0.718%

    No Known Activations