© 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. 22309
    Prev
    Next
    INDEX
    Explanations

    stalking and being stalked

    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
    ä»ħ代表
    -0.09
     VOID
    -0.09
    lad
    -0.09
     corrupted
    -0.08
     Hosp
    -0.08
    ä¸Ģç¯ĩ
    -0.08
    tube
    -0.08
    íģIJ
    -0.08
    amide
    -0.08
     Ramp
    -0.08
    POSITIVE LOGITS
    çĽ¯
    0.15
     dõi
    0.12
     spy
    0.11
    çĽijè§Ĩ
    0.11
    è·Łè¸ª
    0.10
    è¿Ļ个èģĮä¸ļ
    0.10
    追éļı
    0.10
    èIJ½åIJİ
    0.10
    追踪
    0.10
    追
    0.10
    Activations Density 0.224%

    No Known Activations