© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9055
    Prev
    Next
    INDEX
    Explanations

    positive descriptors

    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
    騰
    -0.09
    å°±å¤Ł
    -0.09
     APS
    -0.08
    åŀĤ
    -0.08
    ä»Ļå¢ĥ
    -0.08
    attle
    -0.08
    ä¸ĢæĿ¡é¾Ļ
    -0.08
    éŃĶæ³ķ
    -0.08
    çĬ¹å¦Ĥ
    -0.08
    otts
    -0.08
    POSITIVE LOGITS
    ÑIJ
    0.10
    æıIJæĹ©
    0.09
    åħįè´£
    0.08
    请æĤ¨
    0.08
    ëŁ¼
    0.08
    esModule
    0.08
    OURS
    0.08
    bur
    0.08
    pty
    0.08
    oc
    0.08
    Activations Density 0.023%

    No Known Activations