© 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. 15340
    Prev
    Next
    INDEX
    Explanations

    can't help but | can't deny

    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
     Rit
    -0.12
     pró
    -0.11
    DS
    -0.11
     forc
    -0.11
     transferring
    -0.11
     Mild
    -0.11
    ToPoint
    -0.11
    alla
    -0.11
    cip
    -0.11
     airy
    -0.11
    POSITIVE LOGITS
     feeling
    0.10
     Feeling
    0.09
     feel
    0.08
    emer
    0.08
     reminis
    0.07
     Kov
    0.07
     feels
    0.07
     churn
    0.07
    æĦŁ
    0.07
     stall
    0.07
    Activations Density 0.003%

    No Known Activations