© 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. 89953
    Prev
    Next
    INDEX
    Explanations

    to [verb]

    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
    lauf
    -0.13
    vang
    -0.11
    RAFT
    -0.11
    ucks
    -0.11
    expl
    -0.11
    lette
    -0.11
    eration
    -0.11
     kend
    -0.11
    igin
    -0.11
    TRS
    -0.11
    POSITIVE LOGITS
     increase
    0.11
     boost
    0.10
     Increase
    0.10
     treat
    0.10
    enh
    0.09
     Enh
    0.09
     enhance
    0.09
    Enh
    0.09
     Boost
    0.09
     calm
    0.08
    Activations Density 0.008%

    No Known Activations