© 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. 111956
    Prev
    Next
    INDEX
    Explanations

    either express or implied

    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
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.13
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.12
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -0.12
    ickey
    -0.12
    ↵↵↵↵↵↵↵↵↵↵↵
    -0.12
     fired
    -0.11
     outward
    -0.11
    andon
    -0.11
     pov
    -0.11
    uppercase
    -0.11
    POSITIVE LOGITS
     human
    0.09
     use
    0.08
     $↵
    0.08
     effectiveness
    0.08
     warranty
    0.07
     product
    0.07
     sale
    0.07
     trial
    0.07
    331
    0.07
     packaging
    0.07
    Activations Density 0.016%

    No Known Activations