© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117204
    Prev
    Next
    INDEX
    Explanations

    embedded tissue

    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
    pst
    -0.09
    -producing
    -0.09
    -themed
    -0.09
    sy
    -0.08
     focused
    -0.08
     colle
    -0.08
     producing
    -0.08
    946
    -0.08
    iani
    -0.08
    connecting
    -0.08
    POSITIVE LOGITS
     imprisoned
    0.14
    -bound
    0.14
    -hidden
    0.13
     protected
    0.13
    rapped
    0.13
     bound
    0.13
     incarcerated
    0.13
    -mounted
    0.13
     concealed
    0.12
     obscured
    0.12
    Activations Density 0.028%

    No Known Activations