© 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. 3606
    Prev
    Next
    INDEX
    Explanations

    Jekyll and Hyde

    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
    åĵī
    -0.09
    cant
    -0.09
    对çĿĢ
    -0.09
    TECT
    -0.08
    èĨº
    -0.08
    æ±²
    -0.08
    aga
    -0.08
    à¸ģาร
    -0.08
    è·¨
    -0.08
    ADS
    -0.08
    POSITIVE LOGITS
    ç©·
    0.10
    ä»»ä½ķ人
    0.10
    YRO
    0.10
    åĹ³
    0.09
    çľĭæ¸ħ
    0.09
    窮
    0.09
    åĭĩ
    0.09
    åĬ¨èį¡
    0.09
     Hond
    0.09
    红楼
    0.09
    Activations Density 0.003%

    No Known Activations