© 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. 114128
    Prev
    Next
    INDEX
    Explanations

    initials followed by name

    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
     Spicer
    -0.12
     TCL
    -0.10
    pla
    -0.10
     enc
    -0.10
     Conditional
    -0.09
    irs
    -0.09
    ],$
    -0.09
     Extr
    -0.09
    obot
    -0.09
    /Base
    -0.09
    POSITIVE LOGITS
    izzle
    0.11
    ibri
    0.09
    à¥į
    0.08
     scri
    0.08
     Penny
    0.08
     regular
    0.08
     dep
    0.08
     fauc
    0.08
     reconnaissance
    0.08
     cigarettes
    0.08
    Activations Density 0.151%

    No Known Activations