© 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. 32498
    Prev
    Next
    INDEX
    Explanations

    relative clauses

    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
    å¦Ĥæľīä¾µæĿĥ
    -0.12
    以èĩ´
    -0.11
    æīĢ以æĪij
    -0.10
    ä½Ĩ她
    -0.10
    æŃ»è§Ĵ
    -0.10
    ä½Ĩå®ĥ
    -0.09
    æ¯ıä¸Ģ个人
    -0.09
    硼
    -0.09
    ä½Ĩå¦Ĥæŀľ
    -0.09
    åħĪéĶĭ
    -0.09
    POSITIVE LOGITS
     meanwhile
    0.10
    ï¼ĮåĪĻ
    0.10
    追æ±Ĥ
    0.09
    erton
    0.08
    åIJij社ä¼ļ
    0.08
    yles
    0.08
    UV
    0.08
    ä¹ŁåĽłæѤ
    0.08
    reff
    0.07
    å¹¿æ³ĽåºĶçĶ¨
    0.07
    Activations Density 0.184%

    No Known Activations