© 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. 47096
    Prev
    Next
    INDEX
    Explanations

    names containing "an"

    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
    dom
    -0.11
    ked
    -0.11
    kle
    -0.10
     Harness
    -0.10
    shal
    -0.10
    chen
    -0.10
    swer
    -0.10
    cheng
    -0.09
     Sunshine
    -0.09
    ly
    -0.09
    POSITIVE LOGITS
    ing
    0.10
    zl
    0.09
    asu
    0.09
    anja
    0.09
     informational
    0.08
    iec
    0.08
    omain
    0.08
    asl
    0.08
     Intellectual
    0.08
    ZN
    0.07
    Activations Density 0.080%

    No Known Activations