© 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. 89621
    Prev
    Next
    INDEX
    Explanations

    curved shapes

    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
    arf
    -0.11
     unrecognized
    -0.09
    uto
    -0.09
     Hub
    -0.09
     nab
    -0.08
     sweeps
    -0.08
    anus
    -0.08
     heel
    -0.08
    vp
    -0.08
     WF
    -0.08
    POSITIVE LOGITS
    pedia
    0.09
     mature
    0.09
     poison
    0.09
    ensch
    0.09
     putt
    0.09
    aceous
    0.09
     dich
    0.09
     hypnot
    0.09
     Stops
    0.09
     sneak
    0.09
    Activations Density 0.013%

    No Known Activations