© 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. 52670
    Prev
    Next
    INDEX
    Explanations

    another/whole/one/different + noun

    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
    ç¬ĭ
    -0.09
    æĹłç¼ĺ
    -0.09
    å¹³æ°ij
    -0.09
    UF
    -0.09
    ä¸Ģå®ļæĺ¯
    -0.09
    æĭ
    -0.09
    æĬ¼
    -0.08
    vision
    -0.08
    äºĨä¸Ģæī¹
    -0.08
     Kro
    -0.08
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.12
    åı¦æľī
    0.11
    åı¦ä¸Ģ
    0.11
    åı¦ä¸Ģæĸ¹éĿ¢
    0.10
    åı¦
    0.10
     altogether
    0.10
    åı¦å¤ĸ
    0.09
    åı¦ä¸Ģè¾¹
    0.09
    riba
    0.09
     matter
    0.09
    Activations Density 0.027%

    No Known Activations