© 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. 91997
    Prev
    Next
    INDEX
    Explanations

    scrutiny and critique

    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
    headed
    -0.10
    oli
    -0.09
    ays
    -0.09
    ellers
    -0.08
    ipi
    -0.08
    annon
    -0.08
    uni
    -0.08
     Bradford
    -0.08
    iba
    -0.08
     dynam
    -0.08
    POSITIVE LOGITS
     scrutiny
    0.19
     scrutin
    0.17
    ospel
    0.12
    izing
    0.11
     scrut
    0.11
     Fon
    0.10
    /select
    0.10
     merciless
    0.10
    jee
    0.10
     Scr
    0.10
    Activations Density 0.005%

    No Known Activations