© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16056
    Prev
    Next
    INDEX
    Explanations

    desperate

    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
     legendary
    -0.10
    ames
    -0.09
     Gaw
    -0.09
    rs
    -0.08
    way
    -0.08
    lic
    -0.08
     authorize
    -0.08
     Elite
    -0.08
    constants
    -0.08
    wer
    -0.08
    POSITIVE LOGITS
     plea
    0.17
     attempts
    0.16
     attempt
    0.16
     situation
    0.16
     situations
    0.15
     desperate
    0.15
     pleas
    0.14
     clinging
    0.13
     hope
    0.13
     Situation
    0.13
    Activations Density 0.019%

    No Known Activations