© 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. 115752
    Prev
    Next
    INDEX
    Explanations

    against

    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
     baggage
    -0.07
     hob
    -0.07
     climbing
    -0.07
     unfold
    -0.07
     zig
    -0.06
     whe
    -0.06
     adher
    -0.06
     gul
    -0.06
     unlock
    -0.06
    ifix
    -0.06
    POSITIVE LOGITS
     constraints
    0.14
     restraint
    0.14
     bindings
    0.13
     confines
    0.13
     bonds
    0.13
    straints
    0.13
     unsuccessfully
    0.12
     controls
    0.12
     ropes
    0.12
     futile
    0.12
    Activations Density 0.018%

    No Known Activations