© 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. 114994
    Prev
    Next
    INDEX
    Explanations

    curious, uninitiated, or offended

    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
    alog
    -0.08
    zel
    -0.08
    lag
    -0.08
    icher
    -0.07
    727
    -0.07
     hel
    -0.07
     smoothed
    -0.07
     usual
    -0.07
     cro
    -0.07
    cro
    -0.07
    POSITIVE LOGITS
    REA
    0.12
     parent
    0.11
     who
    0.11
     traveller
    0.11
    phe
    0.11
     souls
    0.10
    who
    0.10
    caff
    0.10
     rip
    0.10
    racial
    0.10
    Activations Density 0.005%

    No Known Activations