© 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. 33045
    Prev
    Next
    INDEX
    Explanations

    PW CW GW NW WW LW EW IW RW JW

    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
     VIC
    -0.11
     DIC
    -0.11
    PMC
    -0.11
     Bates
    -0.11
     ACA
    -0.11
     scp
    -0.10
    lotte
    -0.10
     CPL
    -0.10
    MMC
    -0.09
     TAS
    -0.09
    POSITIVE LOGITS
     CW
    0.45
     PW
    0.44
     LW
    0.43
    CW
    0.43
     RW
    0.42
     IW
    0.42
     EW
    0.40
    PW
    0.39
     GW
    0.39
     JW
    0.39
    Activations Density 0.928%

    No Known Activations