© 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. 16822
    Prev
    Next
    INDEX
    Explanations

    names preceded by 'Mer' or 'of'

    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
     civilians
    -0.11
     hers
    -0.10
    ByEmail
    -0.09
    Reporter
    -0.08
     civilian
    -0.08
    ilden
    -0.08
    /--
    -0.08
     Pelosi
    -0.08
     granny
    -0.08
    tracer
    -0.08
    POSITIVE LOGITS
     Jaime
    0.08
    iro
    0.08
     Tata
    0.08
     RelayCommand
    0.07
    his
    0.07
     his
    0.07
    olut
    0.07
    ues
    0.07
    tbl
    0.07
    à±
    0.07
    Activations Density 3.998%

    No Known Activations