© 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. 27400
    Prev
    Next
    INDEX
    Explanations

    radio frequency and radioactive

    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
    å¿ĥæĦ¿
    -0.10
    åĻ¬
    -0.09
    rschein
    -0.09
    çĦ°
    -0.09
    èħ¥
    -0.08
    Hands
    -0.08
    Anywhere
    -0.08
     Hands
    -0.08
    æľīä¸Ģ次
    -0.08
    åį³ä¾¿
    -0.08
    POSITIVE LOGITS
    åªĴä»ĭ
    0.09
    atts
    0.09
     пÑĢоÑģ
    0.09
    arta
    0.09
    orks
    0.09
    çīĩåĪ»
    0.08
    ç½®äºİ
    0.08
    ORK
    0.08
    éĢ¼
    0.08
    模仿
    0.08
    Activations Density 0.437%

    No Known Activations