© 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. 33664
    Prev
    Next
    INDEX
    Explanations

    and or

    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
     ifs
    -0.11
    377
    -0.10
    fa
    -0.10
     hybrids
    -0.10
    rom
    -0.10
    iga
    -0.10
    ute
    -0.10
    fter
    -0.10
    ieber
    -0.10
     FileAccess
    -0.10
    POSITIVE LOGITS
    /or
    0.14
     other
    0.10
    amp
    0.09
     optionally
    0.08
    -/
    0.08
     socio
    0.08
    iT
    0.08
     autres
    0.07
    .".
    0.07
     Soc
    0.07
    Activations Density 1.589%

    No Known Activations