© 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. 112254
    Prev
    Next
    INDEX
    Explanations

    don't verb

    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
     Grat
    -0.10
     oppos
    -0.10
     trag
    -0.08
    aga
    -0.08
     twisting
    -0.08
    kker
    -0.08
    zza
    -0.08
     oblivious
    -0.08
     starving
    -0.08
     somew
    -0.08
    POSITIVE LOGITS
     incomplete
    0.12
     dishonest
    0.11
     voluntarily
    0.10
     Rodrigo
    0.10
     unfinished
    0.10
     intolerance
    0.10
    Incomplete
    0.10
     resort
    0.10
    Such
    0.10
     unresolved
    0.10
    Activations Density 0.039%

    No Known Activations