© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7233
    Prev
    Next
    INDEX
    Explanations

    ensure better condition

    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
    è¶³å¤ŁçļĦ
    -0.08
    AN
    -0.08
    idas
    -0.08
    çļĦ巨大
    -0.08
    èħĭ
    -0.07
    çijĽ
    -0.07
    æĶ¾ç¼ĵ
    -0.07
    ä¿Ł
    -0.07
    bic
    -0.07
    è¶³å¤Ł
    -0.07
    POSITIVE LOGITS
    è¿Ļæł·æīįèĥ½
    0.12
    å°½åı¯èĥ½
    0.11
    éķ¿å¯¿
    0.11
    顺åĪ©
    0.10
    顺åĪ©å®ĮæĪIJ
    0.10
    享åıĹ
    0.10
    å®īå¿ĥ
    0.10
    ä¸įå¤ļ
    0.09
    çļĦå¿ĥæĥħ
    0.09
    享åıĹåĪ°
    0.09
    Activations Density 0.154%

    No Known Activations