© 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. 16553
    Prev
    Next
    INDEX
    Explanations

    fucking up or around

    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
     Rin
    -0.09
     unsur
    -0.09
    aille
    -0.09
    oure
    -0.09
    esso
    -0.08
    ODO
    -0.08
     spl
    -0.08
    GH
    -0.08
    iid
    -0.08
    NU
    -0.08
    POSITIVE LOGITS
     around
    0.13
    /date
    0.11
     up
    0.11
     someone
    0.11
     royalty
    0.10
     somebody
    0.10
    916
    0.10
     away
    0.09
     loose
    0.09
     Around
    0.09
    Activations Density 0.006%

    No Known Activations