© 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. 28676
    Prev
    Next
    INDEX
    Explanations

    activist, Cech, Nintendo, hormones, policy

    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
    ,âĢ¦↵↵
    -0.11
    Guest
    -0.10
     Jord
    -0.10
     Gad
    -0.10
     Sau
    -0.10
     whilst
    -0.10
     Mam
    -0.09
    quo
    -0.09
    hee
    -0.09
     [âĢ¦]↵↵
    -0.09
    POSITIVE LOGITS
    kas
    0.08
     Peel
    0.08
    indle
    0.08
    ahir
    0.08
     bro
    0.08
     whe
    0.07
     <$
    0.07
    ailer
    0.07
    edef
    0.07
    Another
    0.07
    Activations Density 0.035%

    No Known Activations