© 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. 17607
    Prev
    Next
    INDEX
    Explanations

    what the fuck is

    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
     precise
    -0.08
     MVP
    -0.08
    ysi
    -0.08
     WTF
    -0.08
    675
    -0.08
     syn
    -0.08
    -wh
    -0.08
    fts
    -0.07
    iores
    -0.07
     dare
    -0.07
    POSITIVE LOGITS
    ckt
    0.14
    igram
    0.11
     chalk
    0.11
    ceu
    0.10
    elay
    0.10
    (EXPR
    0.10
    ìļĶ
    0.10
    ...↵↵↵↵
    0.10
     Req
    0.10
    /dis
    0.09
    Activations Density 0.002%

    No Known Activations