© 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. 26702
    Prev
    Next
    INDEX
    Explanations

    worth it

    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
    uru
    -0.10
    licht
    -0.10
     unb
    -0.10
     pov
    -0.09
     pars
    -0.09
    xing
    -0.09
     Nes
    -0.09
    anga
    -0.09
     symmetry
    -0.09
    raph
    -0.08
    POSITIVE LOGITS
     worth
    0.55
     Worth
    0.51
     worthwhile
    0.42
    worth
    0.40
     payoff
    0.25
     reward
    0.25
     outweigh
    0.25
     rewarding
    0.25
     rewards
    0.23
     justify
    0.22
    Activations Density 0.157%

    No Known Activations