© 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. 90250
    Prev
    Next
    INDEX
    Explanations

    worth or deserving

    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
    vero
    -0.10
     seg
    -0.09
    undy
    -0.09
    rian
    -0.09
    ordin
    -0.08
    tsy
    -0.08
     obedient
    -0.08
    riel
    -0.08
    oge
    -0.08
    ieu
    -0.08
    POSITIVE LOGITS
     worth
    0.68
     Worth
    0.55
     worthwhile
    0.50
     worthy
    0.50
    worth
    0.47
     deserving
    0.40
     deserve
    0.36
     deserves
    0.35
    worthy
    0.33
    -worthy
    0.33
    Activations Density 0.377%

    No Known Activations