© 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. 91160
    Prev
    Next
    INDEX
    Explanations

    filter chain

    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
    .cv
    -0.07
    ód
    -0.07
     dispatch
    -0.07
    cq
    -0.07
    -Bar
    -0.07
     tear
    -0.06
     McCl
    -0.06
     cess
    -0.06
     #
    -0.06
    tones
    -0.06
    POSITIVE LOGITS
     unders
    0.12
    (strict
    0.10
     =↵↵
    0.10
     refr
    0.10
     honoured
    0.10
     LENG
    0.10
     Andres
    0.09
    undred
    0.09
    ierten
    0.09
     hundred
    0.09
    Activations Density 0.002%

    No Known Activations