© 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. 7315
    Prev
    Next
    INDEX
    Explanations

    Cha/Ba followed by names

    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
    e
    -0.12
    eus
    -0.12
    ulis
    -0.11
    ffe
    -0.10
    o
    -0.10
    gra
    -0.10
    zik
    -0.10
    eon
    -0.10
    ea
    -0.10
    thest
    -0.10
    POSITIVE LOGITS
    iley
    0.11
     bent
    0.09
     skl
    0.09
     Xiao
    0.09
    erk
    0.09
    heiten
    0.09
    ixin
    0.09
    Da
    0.09
    quet
    0.09
    ughter
    0.09
    Activations Density 0.032%

    No Known Activations