© 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. 20260
    Prev
    Next
    INDEX
    Explanations

    long hair, shoulders

    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
    ç»Ĩå¾®
    -0.10
    åĶĩ
    -0.10
    å¾®å¦Ļ
    -0.09
    è¿ĺä¸įéĶĻ
    -0.09
    åĴĮåıijå±ķ
    -0.08
    åı¯è§Ĥ
    -0.08
    ä¸įå°ıçļĦ
    -0.08
    orts
    -0.08
     Cra
    -0.08
    resher
    -0.08
    POSITIVE LOGITS
    çģ«çĤ¬
    0.12
    agens
    0.10
    èIJ½
    0.10
    caret
    0.09
    è¶ħ
    0.09
    ä¿Ŀå§Ĩ
    0.09
    ள
    0.09
    -clear
    0.08
    à¹Ħร
    0.08
    辫
    0.08
    Activations Density 0.061%

    No Known Activations