© 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. 47425
    Prev
    Next
    INDEX
    Explanations

    DAC interface, DacGen, Zac, acurius

    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
    erot
    -0.12
    es
    -0.12
    y
    -0.12
    ingham
    -0.10
    ensively
    -0.10
    ing
    -0.10
    iad
    -0.10
    edis
    -0.10
    tg
    -0.09
    uge
    -0.09
    POSITIVE LOGITS
    CORD
    0.14
    al
    0.13
    intosh
    0.12
    dac
    0.12
    oon
    0.11
    lient
    0.11
    enta
    0.11
    unar
    0.11
    adena
    0.11
    ulty
    0.11
    Activations Density 0.176%

    No Known Activations