© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31680
    Prev
    Next
    INDEX
    Explanations

    scores or ratings

    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
     out
    -0.13
    #/
    -0.12
    /U
    -0.11
    $/
    -0.11
     #'
    -0.11
    OutOf
    -0.11
    aggi
    -0.11
    .divide
    -0.10
    crud
    -0.10
     /(
    -0.10
    POSITIVE LOGITS
    ths
    0.13
     stars
    0.10
     IGN
    0.10
     lust
    0.09
    imest
    0.08
    pts
    0.08
    chal
    0.08
     lean
    0.08
    774
    0.07
     points
    0.07
    Activations Density 0.059%

    No Known Activations