© 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. 16749
    Prev
    Next
    INDEX
    Explanations

    Independence

    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
    yers
    -0.10
    iac
    -0.09
     libre
    -0.09
     Strict
    -0.08
     Thi
    -0.08
    ownt
    -0.08
     Rosenberg
    -0.08
    /media
    -0.08
    akk
    -0.08
    nero
    -0.08
    POSITIVE LOGITS
     assortment
    0.12
    ending
    0.11
    ently
    0.11
    endent
    0.10
    ENTA
    0.10
     Spirits
    0.10
     unb
    0.10
     justified
    0.10
    edia
    0.10
     alto
    0.10
    Activations Density 0.035%

    No Known Activations