© 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. 114335
    Prev
    Next
    INDEX
    Explanations

    when/if followed by conditional outcome

    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
     tore
    -0.09
     dreaded
    -0.08
    vil
    -0.08
     coveted
    -0.08
     slugg
    -0.08
    ived
    -0.08
     spilled
    -0.08
    entin
    -0.07
     dwind
    -0.07
    anning
    -0.07
    POSITIVE LOGITS
     unable
    0.24
     able
    0.24
     done
    0.17
    /as
    0.17
     aware
    0.17
     taken
    0.16
     surrounded
    0.16
     located
    0.15
     prone
    0.15
     capable
    0.15
    Activations Density 0.288%

    No Known Activations