© 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. 116984
    Prev
    Next
    INDEX
    Explanations

    coupling, coumarins, variable coupling

    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
     priv
    -0.10
    cow
    -0.09
    GBK
    -0.09
    atory
    -0.09
     favourite
    -0.09
     disgusted
    -0.09
    race
    -0.09
    encing
    -0.09
    occo
    -0.08
     Buddha
    -0.08
    POSITIVE LOGITS
    /single
    0.09
    oux
    0.09
     dozen
    0.09
     gaz
    0.09
    variably
    0.09
    urent
    0.09
    gom
    0.09
    edic
    0.09
    fos
    0.09
    dera
    0.09
    Activations Density 0.046%

    No Known Activations