© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11135
    Prev
    Next
    INDEX
    Explanations

    inflict, affliction, suffering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    帷
    -0.11
     ÑĦакÑĤ
    -0.10
    éºĿ
    -0.09
    .utc
    -0.09
    好å¤Ħ
    -0.09
    çĴ©
    -0.09
     chuyá»ĩn
    -0.09
    äºĭåIJİ
    -0.08
    isci
    -0.08
    flight
    -0.08
    POSITIVE LOGITS
    еб
    0.11
    iveness
    0.10
    ively
    0.10
    atable
    0.10
    tes
    0.09
    uate
    0.09
    ÑĤен
    0.09
    toolbox
    0.09
    ution
    0.08
    ives
    0.08
    Activations Density 0.024%

    No Known Activations