© 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. 31750
    Prev
    Next
    INDEX
    Explanations

    bending and accelerating

    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
    trag
    -0.10
     unde
    -0.09
     cannons
    -0.09
     polo
    -0.09
    -decoration
    -0.09
    dal
    -0.08
     unregister
    -0.08
     Mack
    -0.08
    ingly
    -0.08
    oki
    -0.08
    POSITIVE LOGITS
     backs
    0.13
     down
    0.12
     knees
    0.12
    -over
    0.11
     Lum
    0.10
    dle
    0.10
     back
    0.10
     knee
    0.10
     over
    0.10
     backed
    0.10
    Activations Density 0.003%

    No Known Activations