© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113715
    Prev
    Next
    INDEX
    Explanations

    Zhang and Chinese names

    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
     cry
    -0.10
    ael
    -0.09
     Trafford
    -0.08
    iser
    -0.08
     Cry
    -0.08
    search
    -0.08
    uat
    -0.08
     grind
    -0.08
    uste
    -0.08
    istik
    -0.08
    POSITIVE LOGITS
    former
    0.11
    sun
    0.10
     withheld
    0.09
     Oversight
    0.09
     gul
    0.08
     deferred
    0.08
     å¼
    0.08
    tics
    0.08
     Zug
    0.08
     Unter
    0.08
    Activations Density 0.010%

    No Known Activations