© 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. 5175
    Prev
    Next
    INDEX
    Explanations

    decisions and potential actions

    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
     rather
    -0.09
    ochen
    -0.09
    imus
    -0.09
    inan
    -0.08
     pav
    -0.08
    inen
    -0.08
     Hers
    -0.08
     Pav
    -0.07
     gost
    -0.07
     unless
    -0.07
    POSITIVE LOGITS
     potentially
    0.15
     blindly
    0.15
     risking
    0.14
     possibly
    0.14
     Possibly
    0.14
     risk
    0.13
     anonymously
    0.13
    /wait
    0.13
     continue
    0.12
     thereby
    0.12
    Activations Density 0.120%

    No Known Activations