© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 26442
    Prev
    Next
    INDEX
    Explanations

    wherein relative clauses

    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
    让èĩªå·±
    -0.09
    reamble
    -0.09
    对èĩªå·±
    -0.09
    对æĪij们
    -0.09
    æĦ¿æĦı
    -0.08
    ãģ£ãģ¦ãģĹãģ¾ãģ£ãģŁ
    -0.08
    andelier
    -0.08
    .ByteArray
    -0.08
    èħĭ
    -0.08
    è¿
    -0.08
    POSITIVE LOGITS
    åIJĦé¡¹å·¥ä½ľ
    0.10
    æį¢æĿ¥
    0.09
    å¤ļç§į
    0.09
    å¾Ĺèµ·
    0.09
    注æĦıåĬĽ
    0.08
    å¾Īå¿«
    0.08
    åħ±åIJĮåıijå±ķ
    0.08
    æĭīæĸ¯
    0.08
    æĸ°çļĦ
    0.08
     денег
    0.08
    Activations Density 0.752%

    No Known Activations