© 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. 33311
    Prev
    Next
    INDEX
    Explanations

    border security and crossings

    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
    ç¼ļ
    -0.11
    åľ¨æł¡
    -0.11
    æ·ĺæ±°
    -0.10
    尾巴
    -0.10
    ä¸¤åĽ½
    -0.10
    rtl
    -0.10
    ç»Ń约
    -0.10
    çĥĥ
    -0.10
    缫
    -0.09
    èŀįåªĴä½ĵ
    -0.09
    POSITIVE LOGITS
    å¸ĥ
    0.08
    bé
    0.08
    ãģ£ãģ
    0.08
    UCT
    0.07
     Alejandro
    0.07
    SYM
    0.07
    ector
    0.07
    æĥħ
    0.07
     cred
    0.07
    æľĭåıĭ
    0.07
    Activations Density 0.013%

    No Known Activations