© 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. 15430
    Prev
    Next
    INDEX
    Explanations

    it's up to

    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
    ree
    -0.11
     bree
    -0.11
    ongyang
    -0.10
    tti
    -0.10
     automat
    -0.10
    oshi
    -0.10
    -target
    -0.10
    (NS
    -0.10
    imei
    -0.10
    ogo
    -0.10
    POSITIVE LOGITS
     responsibility
    0.26
     duty
    0.25
     incumbent
    0.22
     Duty
    0.19
     Responsibility
    0.19
    respons
    0.17
     obligation
    0.17
     responsibilities
    0.16
     tasked
    0.16
     task
    0.15
    Activations Density 0.184%

    No Known Activations