© 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. 117189
    Prev
    Next
    INDEX
    Explanations

    lu chan, lu and, lu isafolosofololu, luetten, luoluopo

    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
    illon
    -0.10
    andard
    -0.09
     Examiner
    -0.09
    aal
    -0.09
     rex
    -0.08
    blas
    -0.08
    iled
    -0.08
     fours
    -0.08
     Kitt
    -0.08
    four
    -0.08
    POSITIVE LOGITS
    igi
    0.11
    engo
    0.10
    ence
    0.10
    cent
    0.10
    ymes
    0.10
     ingen
    0.10
    onde
    0.10
    cre
    0.10
     Pey
    0.09
    cret
    0.09
    Activations Density 0.059%

    No Known Activations