© 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. 32809
    Prev
    Next
    INDEX
    Explanations

    passing through or going through

    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¿ľæĸ¹
    -0.12
    è¡įçĶŁ
    -0.10
    çĤ¬
    -0.10
    客æĪ·æıIJä¾Ľ
    -0.10
    _capacity
    -0.10
    顺åĬ¿
    -0.10
    ç¥ŀå·ŀ
    -0.09
    ESC
    -0.09
    å®Įç¾İçļĦ
    -0.09
    æĪŁ
    -0.09
    POSITIVE LOGITS
    ç©¿è¶Ĭ
    0.12
    ä¸Ģ段
    0.11
    ç©¿è¿ĩ
    0.10
    è¿ĩäºĨ
    0.10
    è¶Ĭè¿ĩ
    0.10
    åįĸæİī
    0.10
     passage
    0.09
    æ¶īåıĬ
    0.09
    éģĩä¸Ĭ
    0.09
    æ¶ī
    0.09
    Activations Density 0.220%

    No Known Activations