© 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. 91715
    Prev
    Next
    INDEX
    Explanations

    "lost" or "irony" following negation

    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
     concession
    -0.10
     rekl
    -0.10
     пеÑĢем
    -0.10
    ran
    -0.09
    uka
    -0.09
    oom
    -0.09
    gings
    -0.09
     pou
    -0.09
    olt
    -0.09
     concessions
    -0.09
    POSITIVE LOGITS
     neither
    0.14
     none
    0.12
     not
    0.11
     won
    0.10
     NOT
    0.10
     wont
    0.10
    ÐĿе
    0.10
    -none
    0.10
     NONE
    0.10
    	not
    0.10
    Activations Density 0.005%

    No Known Activations