© 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. 46486
    Prev
    Next
    INDEX
    Explanations

    words or states indicating a lack of something

    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
    bomb
    -0.12
    -sized
    -0.10
    isation
    -0.10
    izing
    -0.09
     Castro
    -0.09
    erm
    -0.09
     undis
    -0.09
     ongoing
    -0.09
     uninterrupted
    -0.09
     toned
    -0.09
    POSITIVE LOGITS
    /un
    0.27
    /il
    0.16
    /non
    0.13
    /out
    0.12
    /not
    0.11
    /misc
    0.11
    /off
    0.11
    /no
    0.11
    /conf
    0.11
    /in
    0.11
    Activations Density 0.522%

    No Known Activations