© 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. 88091
    Prev
    Next
    INDEX
    Explanations

    regardless

    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
     BUT
    -0.13
     yet
    -0.12
     Yet
    -0.11
     Coy
    -0.11
    but
    -0.10
    yet
    -0.10
    Yet
    -0.10
    ,but
    -0.10
    —but
    -0.10
     pit
    -0.10
    POSITIVE LOGITS
     thats
    0.20
     THAT
    0.17
     suffice
    0.14
    —that
    0.13
     That
    0.13
     regardless
    0.13
     enough
    0.13
     suff
    0.12
     outweigh
    0.12
     therefore
    0.12
    Activations Density 0.209%

    No Known Activations