© 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. 27034
    Prev
    Next
    INDEX
    Explanations

    negative situations

    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
    rush
    -0.10
    å®īåħ¨äºĭæķħ
    -0.10
    交æµģåIJĪä½ľ
    -0.09
    ä¿Ń
    -0.09
    ãģ«æĪ
    -0.09
    Ãłnh
    -0.09
    å¾Ī好
    -0.09
    zial
    -0.08
    å¾Īæ¼Ĥ亮
    -0.08
     THEORY
    -0.08
    POSITIVE LOGITS
    /problems
    0.14
    çĥ¦æģ¼
    0.13
     problems
    0.11
    è¿ĻäºĽéĹ®é¢ĺ
    0.11
    çļĦä¸ĢåĪĩ
    0.10
    åħ¶å®ĥéĹ®é¢ĺ
    0.10
    æĮ¤
    0.10
    忧
    0.10
     problemas
    0.10
    ä¸įæŃ»
    0.09
    Activations Density 0.044%

    No Known Activations