© 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. 35651
    Prev
    Next
    INDEX
    Explanations

    emergency response

    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§Ĥå¯Ł
    -0.10
    宽
    -0.09
    ìłĪ
    -0.09
    spo
    -0.09
    inki
    -0.08
    åĿ¯
    -0.08
    Spo
    -0.08
     cpp
    -0.08
    anj
    -0.08
    被åĪ¤
    -0.08
    POSITIVE LOGITS
    åĵįåºĶ
    0.17
    å¥Ķèµ´
    0.16
    åı¬
    0.14
    赶赴
    0.14
    åı¬åĶ¤
    0.13
    积æŀģåĵįåºĶ
    0.13
    éŁ¿
    0.13
    æİ¥åĪ°
    0.12
     respond
    0.12
     responding
    0.12
    Activations Density 0.055%

    No Known Activations