© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 31630
    Prev
    Next
    INDEX
    Explanations

    pornography and academic topics

    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
     Zy
    -0.10
     #'
    -0.10
     (&
    -0.09
    )throws
    -0.09
    )t
    -0.09
     (?)
    -0.09
       
    -0.09
     aire
    -0.08
    +".
    -0.08
     Hicks
    -0.08
    POSITIVE LOGITS
    ↵↵
    0.19
    ↵
    0.18
    ↵↵↵
    0.13
    »↵↵
    0.10
    ...↵
    0.10
    â̦↵
    0.09
    ?↵
    0.09
    []↵
    0.09
    =↵↵
    0.09
     []↵
    0.09
    Activations Density 0.133%

    No Known Activations