© 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. 31297
    Prev
    Next
    INDEX
    Explanations

    by a considerable amount

    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
    chen
    -0.12
    lesia
    -0.12
    584
    -0.10
     Oak
    -0.09
    onga
    -0.09
    ubo
    -0.09
     paran
    -0.09
     Vac
    -0.09
    erez
    -0.09
     setattr
    -0.08
    POSITIVE LOGITS
     far
    0.35
    far
    0.28
     by
    0.27
     vastly
    0.27
     considerably
    0.26
     FAR
    0.26
     significantly
    0.22
     definitely
    0.22
     substantially
    0.21
    Far
    0.20
    Activations Density 0.255%

    No Known Activations