© 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. 31677
    Prev
    Next
    INDEX
    Explanations

    allowing support

    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
     Craigslist
    -0.12
     prostitutes
    -0.11
     pornography
    -0.10
     Sutton
    -0.10
     dude
    -0.09
    DVD
    -0.09
     incumbent
    -0.09
     Flesh
    -0.09
     regret
    -0.09
     cush
    -0.09
    POSITIVE LOGITS
    æĤ¨
    0.10
     gerne
    0.10
     dances
    0.10
     Cristiano
    0.10
     educ
    0.09
    iben
    0.09
    emoji
    0.09
    _commands
    0.09
     constructions
    0.09
     softly
    0.09
    Activations Density 0.012%

    No Known Activations