© 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. 48414
    Prev
    Next
    INDEX
    Explanations

    hinge upon or tilt

    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
    ubi
    -0.09
    tram
    -0.08
     Depths
    -0.08
    ksam
    -0.08
    ially
    -0.08
     kenn
    -0.08
     lle
    -0.08
    isted
    -0.07
    uced
    -0.07
     vene
    -0.07
    POSITIVE LOGITS
     balance
    0.13
    (balance
    0.13
    -bal
    0.12
     balancing
    0.12
     tot
    0.12
    balance
    0.12
     precarious
    0.12
     balanced
    0.12
     topp
    0.12
     Balanced
    0.12
    Activations Density 0.001%

    No Known Activations