© 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. 18151
    Prev
    Next
    INDEX
    Explanations

    focused on, arguments over, likely to

    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
     whilst
    -0.08
     Whilst
    -0.08
     epit
    -0.08
     firstly
    -0.08
     ``
    -0.08
     Firstly
    -0.07
    Whilst
    -0.07
    ih
    -0.07
     downfall
    -0.07
     excell
    -0.07
    POSITIVE LOGITS
    /Dk
    0.14
    —"
    0.13
     sadd
    0.13
     folks
    0.13
     kinda
    0.11
     shitty
    0.11
      ↵↵↵
    0.11
     outf
    0.11
     fucked
    0.11
     Dems
    0.11
    Activations Density 0.095%

    No Known Activations