© 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. 46628
    Prev
    Next
    INDEX
    Explanations

    as good as any

    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
     SAME
    -0.12
    itzer
    -0.10
    inh
    -0.10
     Jas
    -0.10
    loh
    -0.09
     grac
    -0.09
     impres
    -0.09
     Same
    -0.09
     likewise
    -0.09
     enlisted
    -0.09
    POSITIVE LOGITS
     anywhere
    0.32
     any
    0.31
     anything
    0.31
    anything
    0.28
    ä»»
    0.27
     anybody
    0.26
    Anything
    0.26
     anyone
    0.25
    any
    0.25
     Anything
    0.24
    Activations Density 0.059%

    No Known Activations