© 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. 27186
    Prev
    Next
    INDEX
    Explanations

    job postings and assignments

    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
    éĿł
    -0.09
    ajs
    -0.09
    _aspect
    -0.08
    è§ĦèĮĥ
    -0.08
    缣
    -0.08
    æķ´é¡¿
    -0.08
    çľĭçĶµè§Ĩ
    -0.08
    ç«ĭæ³ķ
    -0.08
    对æłĩ
    -0.08
    ennen
    -0.08
    POSITIVE LOGITS
    ä»»æķĻ
    0.12
    å²Ĺä½į
    0.12
    åĴĮåľ°åĮº
    0.11
    é¹Ĭ
    0.11
    åģıè¿ľ
    0.11
    assignments
    0.10
    使åij½
    0.10
    æīİæł¹
    0.10
    æ²¹èħ»
    0.10
    宫殿
    0.10
    Activations Density 0.101%

    No Known Activations