© 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. 49487
    Prev
    Next
    INDEX
    Explanations

    types of writing and authors

    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¸Ģç¬ij
    -0.11
    妲
    -0.09
    ä¼Ĭæĸ¯
    -0.09
    ä¸īç»´
    -0.09
    æľ¬çĶ°
    -0.09
    erna
    -0.09
    纣
    -0.09
    _INITIALIZ
    -0.08
    èľĪ
    -0.08
    adesh
    -0.08
    POSITIVE LOGITS
    æ½ľ
    0.09
    åĨĻä½ľ
    0.08
    å°ı说
    0.08
    ä¸Ńä¿¡
    0.08
    ä¸Ģè¶Ł
    0.08
    æIJħ
    0.08
    读èĢħ
    0.08
     Kafka
    0.08
    å¤Ħæĸ¹
    0.08
    æłĩå¿ĹæĢ§
    0.08
    Activations Density 0.253%

    No Known Activations