© 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. 18710
    Prev
    Next
    INDEX
    Explanations

    online access and services

    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
    客æĪ¿
    -0.09
    èĪįå¾Ĺ
    -0.09
    çĽijè§Ĩ
    -0.09
     Ãĸzel
    -0.09
    åĸŁ
    -0.09
    çĶµè§Ĩåı°
    -0.08
    _STORAGE
    -0.08
     MEM
    -0.08
    æ¶ĵ
    -0.08
    ause
    -0.08
    POSITIVE LOGITS
    èĩªåĬ©
    0.15
    便æį·
    0.12
    ç½ijä¸Ĭ
    0.11
     online
    0.10
    åľ¨çº¿
    0.10
    便æ°ij
    0.09
    ç¼´è´¹
    0.09
    线ä¸Ĭ
    0.09
    åľ¨ç½ijä¸Ĭ
    0.09
    é«ĺå³°æľŁ
    0.09
    Activations Density 0.120%

    No Known Activations