© 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. 3410
    Prev
    Next
    INDEX
    Explanations

    identification cards

    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
    æ°Ķ象
    -0.10
    纤
    -0.09
    åIJ¦
    -0.09
    abox
    -0.09
    UNS
    -0.09
    误
    -0.09
    æ¯ı天
    -0.09
    ãĤµãĤ¤
    -0.09
    Outlet
    -0.09
    温æŁĶ
    -0.08
    POSITIVE LOGITS
    è¯ģ件
    0.23
    身份è¯ģ
    0.18
    æĬ¤çħ§
    0.16
    驾驶è¯ģ
    0.13
    éĢļè¡Įè¯ģ
    0.13
    è¯ģ
    0.12
    èŃī
    0.12
    è¿Ļå¼ł
    0.12
    åį¡çīĩ
    0.12
     passports
    0.11
    Activations Density 0.072%

    No Known Activations