© 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. 16032
    Prev
    Next
    INDEX
    Explanations

    good question, good thing, good enough

    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
    piece
    -0.07
    mb
    -0.07
     expertise
    -0.07
    sticks
    -0.07
    ingly
    -0.07
    fft
    -0.06
     excellence
    -0.06
     indeed
    -0.06
     threatening
    -0.06
     und
    -0.06
    POSITIVE LOGITS
    witch
    0.13
    asses
    0.13
     Samar
    0.13
    uffix
    0.13
    ieber
    0.12
    bye
    0.12
     vibes
    0.12
     Neighbor
    0.12
    allback
    0.12
    ugi
    0.12
    Activations Density 0.036%

    No Known Activations