© 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. 48433
    Prev
    Next
    INDEX
    Explanations

    entry point or into entry

    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
     pap
    -0.09
    edb
    -0.09
     Mour
    -0.08
    tras
    -0.08
     Dud
    -0.08
    lest
    -0.08
     extras
    -0.08
    isse
    -0.08
    isset
    -0.08
     stead
    -0.08
    POSITIVE LOGITS
     entry
    0.16
     into
    0.15
     Entry
    0.15
    -entry
    0.13
     Entries
    0.13
     ENTRY
    0.13
     Into
    0.13
    (entry
    0.12
     entries
    0.12
    Entry
    0.12
    Activations Density 0.048%

    No Known Activations