© 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. 51022
    Prev
    Next
    INDEX
    Explanations

    campsites and campgrounds

    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
    æĺ¼
    -0.10
    .Framework
    -0.09
    æªIJ
    -0.09
    èĴĤ
    -0.09
    æķħå±ħ
    -0.09
    è°ģèĥ½
    -0.09
    çĺ¤
    -0.09
    å»Ĭ
    -0.09
    æĬĬæı¡
    -0.09
    _gpu
    -0.08
    POSITIVE LOGITS
    çģ¯åħī
    0.09
    人æ°ij
    0.08
    usted
    0.08
    ech
    0.08
    èŀºæĹĭ
    0.08
    两级
    0.08
    ough
    0.08
    åģ¥åħ¨
    0.08
    大åĬĽæİ¨è¿Ľ
    0.08
    大åĬĽåıijå±ķ
    0.08
    Activations Density 0.015%

    No Known Activations