© 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. 55973
    Prev
    Next
    INDEX
    Explanations

    chase, pursuit, follow, stop

    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
    骨干
    -0.10
    æī©
    -0.09
    amac
    -0.09
    ional
    -0.08
    acy
    -0.08
     kale
    -0.08
    sey
    -0.08
    iscard
    -0.08
     Kale
    -0.08
    ailable
    -0.08
    POSITIVE LOGITS
    追
    0.18
    追赶
    0.15
    追踪
    0.14
    æĮ½
    0.14
    è·Łè¿Ľ
    0.13
    è·Łè¸ª
    0.13
    æĬĵä½ı
    0.13
    追éļı
    0.12
    追éĢIJ
    0.12
    追ãģĦ
    0.12
    Activations Density 0.049%

    No Known Activations