© 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. 48968
    Prev
    Next
    INDEX
    Explanations

    truly custom, unique, authentic, epic, sustainable

    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
     cle
    -0.11
     som
    -0.09
     inst
    -0.08
     Berger
    -0.08
     underlying
    -0.07
     knee
    -0.07
     overl
    -0.07
    -trained
    -0.07
     middle
    -0.07
    -inst
    -0.07
    POSITIVE LOGITS
    /AP
    0.11
     transformative
    0.11
    alion
    0.10
     dequeue
    0.10
    alchemy
    0.10
     exceptional
    0.10
     distinctive
    0.10
    Mes
    0.10
     satisf
    0.10
    urgeon
    0.10
    Activations Density 0.001%

    No Known Activations