© 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. 6854
    Prev
    Next
    INDEX
    Explanations

    Christian Science, peace activist, Wilhelm Alheit

    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
     spell
    -0.09
     attracting
    -0.09
    \'
    -0.09
     Müller
    -0.08
     enf
    -0.08
     Hubbard
    -0.08
    omatic
    -0.08
     Andrews
    -0.08
     extraction
    -0.08
    970
    -0.08
    POSITIVE LOGITS
    _asc
    0.12
    allee
    0.11
     Busy
    0.10
     Lindsey
    0.10
    ï¼ŀ
    0.10
    istrator
    0.10
    lyn
    0.10
    unlink
    0.09
    lich
    0.09
     tops
    0.09
    Activations Density 0.001%

    No Known Activations