© 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. 8227
    Prev
    Next
    INDEX
    Explanations

    perks and benefits

    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
    ä¹į
    -0.09
    ãģĹãģ¾ãģĨ
    -0.08
    wers
    -0.08
     máu
    -0.08
    ONLY
    -0.08
    deo
    -0.08
    ä»ħä¾Ľ
    -0.08
    mia
    -0.08
    ãģĹãģ¾
    -0.08
     Wort
    -0.07
    POSITIVE LOGITS
    nic
    0.11
    ìĤ¬íķŃ
    0.10
    è¨ĢãģĪãģ°
    0.10
    åľ°å¸¦
    0.10
    fully
    0.10
    iful
    0.09
    æĹ®
    0.09
    ful
    0.09
    omatic
    0.09
    åĹĵåŃIJ
    0.09
    Activations Density 0.004%

    No Known Activations