© 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. 115608
    Prev
    Next
    INDEX
    Explanations

    seen or heard

    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
    bes
    -0.09
    ever
    -0.09
     either
    -0.09
    ony
    -0.08
    enses
    -0.08
    rove
    -0.08
    ths
    -0.08
     any
    -0.08
     itself
    -0.08
    uter
    -0.08
    POSITIVE LOGITS
     enough
    0.17
     firsthand
    0.15
     similar
    0.14
     Enough
    0.13
     plenty
    0.13
     worse
    0.13
    /read
    0.11
    similar
    0.11
    Enough
    0.11
     insufficient
    0.10
    Activations Density 0.083%

    No Known Activations