© 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. 27061
    Prev
    Next
    INDEX
    Explanations

    dielectric

    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
    umm
    -0.10
     Bitte
    -0.09
    enzie
    -0.09
    oir
    -0.08
    ary
    -0.08
    ayne
    -0.08
    mente
    -0.08
    curring
    -0.08
     spoil
    -0.08
    -minded
    -0.08
    POSITIVE LOGITS
    lectric
    0.22
    -hard
    0.15
    hard
    0.15
    getic
    0.15
    hl
    0.13
    WithError
    0.13
     bouncing
    0.13
    bold
    0.12
    go
    0.12
    cid
    0.11
    Activations Density 0.056%

    No Known Activations