© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50660
    Prev
    Next
    INDEX
    Explanations

    kidnapping and abduction

    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
     elementary
    -0.09
     Swe
    -0.08
    ä¸Ģ代
    -0.08
    奢ä¾Ī
    -0.08
    æŀģ
    -0.08
    BOTTOM
    -0.08
    )(((
    -0.08
     Hull
    -0.08
    åºķ
    -0.08
    æī«
    -0.08
    POSITIVE LOGITS
     abducted
    0.16
    ç»ijæŀ¶
    0.15
     abduction
    0.15
     kidn
    0.14
     kidnapped
    0.13
    åĬ«
    0.13
    æݳ
    0.12
     kidnapping
    0.11
    çĮ¥
    0.11
    æİ¥éĢģ
    0.11
    Activations Density 0.108%

    No Known Activations