© 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. 18218
    Prev
    Next
    INDEX
    Explanations

    I'm

    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
    ington
    -0.10
     Levin
    -0.09
     His
    -0.09
     clums
    -0.09
     Kah
    -0.08
    clc
    -0.08
    corp
    -0.08
    dl
    -0.08
    513
    -0.08
    irs
    -0.08
    POSITIVE LOGITS
     forbid
    0.13
     bust
    0.12
     tolerated
    0.11
     tolerate
    0.11
     Cot
    0.11
     toler
    0.10
    MB
    0.10
     admon
    0.10
     forb
    0.10
     expressly
    0.10
    Activations Density 0.030%

    No Known Activations