© 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. 50392
    Prev
    Next
    INDEX
    Explanations

    lose weight

    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
     escal
    -0.13
    ulis
    -0.12
    iad
    -0.12
    Growing
    -0.10
     Growing
    -0.10
     liners
    -0.10
     reinforcement
    -0.10
    iola
    -0.10
     Hooks
    -0.10
     escalation
    -0.10
    POSITIVE LOGITS
     weight
    0.21
     pounds
    0.19
     Weight
    0.15
    -weight
    0.14
    weight
    0.14
     unwanted
    0.14
     WEIGHT
    0.13
     lbs
    0.13
    Weight
    0.13
     gained
    0.13
    Activations Density 0.067%

    No Known Activations