© 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. 33325
    Prev
    Next
    INDEX
    Explanations

    watch

    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
    y
    -0.20
    b
    -0.18
    c
    -0.18
    s
    -0.18
    d
    -0.17
    i
    -0.15
    es
    -0.15
    x
    -0.14
    n
    -0.14
    yz
    -0.14
    POSITIVE LOGITS
    legg
    0.10
    hon
    0.09
    haven
    0.09
    -cur
    0.09
    alice
    0.09
     runaway
    0.08
    hog
    0.08
     Nimbus
    0.08
    CAF
    0.08
    meer
    0.08
    Activations Density 0.112%

    No Known Activations