© 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. 32571
    Prev
    Next
    INDEX
    Explanations

    loyal or loyalty

    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
    çĺ¾
    -0.09
    ï¾ŀ
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.08
    è´£
    -0.08
    åĮĨåĮĨ
    -0.08
    è¿Ļå¼ł
    -0.08
    обÑĭ
    -0.08
    ç½ijé¦ĸ页
    -0.08
    éĻĦå±ŀ
    -0.08
     McN
    -0.08
    POSITIVE LOGITS
    åı¯éĿłçļĦ
    0.11
    ä¸Ģè´¯
    0.11
    称
    0.10
    ards
    0.10
    erved
    0.10
    åı¯éĿł
    0.10
    istic
    0.09
    heid
    0.09
    -ish
    0.09
     Enough
    0.09
    Activations Density 0.004%

    No Known Activations