© 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. 11503
    Prev
    Next
    INDEX
    Explanations

    this/these followed by noun phrase

    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
    çľĭçĤ¹
    -0.09
    æī¬
    -0.09
    ä¸Ģ身
    -0.08
    ä¸Ģçīĩ
    -0.08
    èĪħ
    -0.08
    è¿Ŀ纪
    -0.08
    æ§IJ
    -0.08
    ÙĪز
    -0.08
    iera
    -0.08
    çĺµ
    -0.08
    POSITIVE LOGITS
    ä½łåĸľæ¬¢
    0.09
    殿åłĤ
    0.09
    è¯Ŀ说
    0.08
    好å¤Ħ
    0.08
    æĪij们å¿ħé¡»
    0.08
     Derek
    0.08
    çľģæĶ¿åºľ
    0.08
    æĪijä»¬åľ¨
    0.08
    _DX
    0.08
    à¹ģหละ
    0.08
    Activations Density 0.033%

    No Known Activations