© 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. 48339
    Prev
    Next
    INDEX
    Explanations

    noun followed by possessive/descriptive word

    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
     complied
    -0.11
     Bew
    -0.10
     Ber
    -0.10
     hastily
    -0.10
     compliant
    -0.10
    oha
    -0.09
     /↵
    -0.09
     reluctantly
    -0.09
     obedient
    -0.09
     complying
    -0.09
    POSITIVE LOGITS
    bull
    0.10
     appoint
    0.09
     subsid
    0.09
     alternate
    0.09
     collateral
    0.09
     defer
    0.09
     bull
    0.08
     Ronnie
    0.08
     further
    0.08
    578
    0.08
    Activations Density 0.002%

    No Known Activations