© 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. 48117
    Prev
    Next
    INDEX
    Explanations

    last thing I want

    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
     Propel
    -0.10
     Mem
    -0.10
     Ot
    -0.10
     hopefully
    -0.10
    azine
    -0.10
     irresistible
    -0.10
     zar
    -0.10
     gleich
    -0.09
    uje
    -0.09
    isd
    -0.09
    POSITIVE LOGITS
     imaginable
    0.13
     EVER
    0.13
     ever
    0.12
    -ever
    0.10
     (<
    0.09
     misd
    0.09
     remot
    0.09
     expected
    0.09
     conscious
    0.09
     anything
    0.09
    Activations Density 0.011%

    No Known Activations