© 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. 27905
    Prev
    Next
    INDEX
    Explanations

    PlayStation 4

    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
     Trump
    -0.13
     Brexit
    -0.13
    Trump
    -0.12
     Ivanka
    -0.11
     Donald
    -0.10
     cellForRowAt
    -0.09
     WikiLeaks
    -0.09
    -Trump
    -0.09
    Donald
    -0.09
     Bannon
    -0.09
    POSITIVE LOGITS
     forState
    0.15
     NSA
    0.13
     forControlEvents
    0.13
    SectionsIn
    0.13
     cellForRowAtIndexPath
    0.12
    FontOfSize
    0.12
     Vine
    0.12
    instagram
    0.12
     WebView
    0.12
     Ferguson
    0.12
    Activations Density 1.330%

    No Known Activations