© 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. 15350
    Prev
    Next
    INDEX
    Explanations

    negative qualifiers

    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
     disappoint
    -0.16
     controversial
    -0.16
     undesirable
    -0.15
     disappointing
    -0.14
     problematic
    -0.14
     questionable
    -0.14
     disappointment
    -0.14
     drawbacks
    -0.13
     disappointed
    -0.13
     mischief
    -0.13
    POSITIVE LOGITS
     suicidal
    0.17
     worse
    0.15
     outright
    0.14
     murderous
    0.14
     physically
    0.13
     suicide
    0.13
     blackmail
    0.12
     violent
    0.12
     homic
    0.12
     poison
    0.12
    Activations Density 0.261%

    No Known Activations