© 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. 113582
    Prev
    Next
    INDEX
    Explanations

    category lists and file path separators

    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
     grues
    -0.12
     typ
    -0.12
     specialised
    -0.12
     prostit
    -0.12
     prostitutes
    -0.11
     tranny
    -0.11
     delights
    -0.11
    ruk
    -0.11
    cks
    -0.11
     specialized
    -0.11
    POSITIVE LOGITS
     dialogue
    0.09
     Caucasian
    0.08
     pov
    0.08
     ---↵
    0.07
     nervous
    0.07
     Hyper
    0.07
     fast
    0.07
     âĢİ
    0.07
     teamwork
    0.07
    emy
    0.07
    Activations Density 0.050%

    No Known Activations