© 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. 63505
    Prev
    Next
    INDEX
    Explanations

    legal sentences and consequences

    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
    积æŀģåĵįåºĶ
    -0.10
    åĨ¤
    -0.09
    åĬ¡
    -0.09
    è¹Ħ
    -0.09
    è´¢æĶ¿éĥ¨
    -0.09
    èݽ
    -0.09
    ä¸Ģè½®
    -0.08
    uds
    -0.08
    äºĭå®ľ
    -0.08
    丢
    -0.08
    POSITIVE LOGITS
     suspicion
    0.09
    Susp
    0.09
    å¯Įæ°ij
    0.09
    éĢĽè¡Ĺ
    0.09
    ä¸į妨
    0.09
    è¿Ļä¸ªåľ°åĽ¾
    0.09
    OrFail
    0.09
    延éķ¿
    0.09
    强åĪ¶
    0.08
    æŁ¥çľĭåħ¨æĸĩ
    0.08
    Activations Density 0.129%

    No Known Activations