© 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. 61214
    Prev
    Next
    INDEX
    Explanations

    collective class/action/hysteria/bargaining

    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
    atics
    -0.09
    دÙĨÙĬ
    -0.09
    è¿ĩçļĦ
    -0.09
    ضة
    -0.08
    неÑĨ
    -0.08
     Eh
    -0.08
    combe
    -0.08
    etta
    -0.08
    eldo
    -0.08
    uits
    -0.08
    POSITIVE LOGITS
    ibri
    0.11
    èµ·æĿ¥
    0.11
    -minded
    0.11
    ively
    0.11
    èµ·ä¾Ĩ
    0.11
    ä¿©
    0.10
    主ä¹īèĢħ
    0.10
    istic
    0.10
    èĢĮè¨Ģ
    0.10
    aneously
    0.10
    Activations Density 0.016%

    No Known Activations