© 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. 29775
    Prev
    Next
    INDEX
    Explanations

    nor or unlike

    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
     anything
    -0.09
    especially
    -0.09
     especially
    -0.09
    _loc
    -0.09
     Com
    -0.09
     con
    -0.08
    548
    -0.08
    KE
    -0.08
     loc
    -0.08
    ampo
    -0.08
    POSITIVE LOGITS
     Nor
    0.21
     nor
    0.20
     like
    0.18
    Nor
    0.17
     unlike
    0.17
    nor
    0.17
    åĥı
    0.15
     Unlike
    0.14
     NOR
    0.13
    Unlike
    0.12
    Activations Density 0.176%

    No Known Activations