© 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. 16824
    Prev
    Next
    INDEX
    Explanations

    I was wondering

    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
     hadn
    -0.20
     had
    -0.12
     Ive
    -0.10
    Had
    -0.10
     has
    -0.10
    had
    -0.09
     habÃŃa
    -0.09
     ive
    -0.09
    've
    -0.08
     Had
    -0.08
    POSITIVE LOGITS
     previously
    0.12
     Instrument
    0.11
    appropri
    0.11
    dl
    0.11
    vals
    0.11
    DDL
    0.11
     Rudd
    0.11
    strument
    0.10
    ipl
    0.10
    WS
    0.10
    Activations Density 0.280%

    No Known Activations