© 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. 52185
    Prev
    Next
    INDEX
    Explanations

    racing, fundraiser, owner, boy, trek

    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
    åŀĥåľ¾æ¡¶
    -0.10
    åĪĽ
    -0.10
    çŃ¼
    -0.09
    伤åı£
    -0.08
    hattan
    -0.08
    nable
    -0.08
    çĢijå¸ĥ
    -0.08
    å¤Ķ
    -0.08
    åľ°ä¸Ńæµ·
    -0.08
     bicy
    -0.08
    POSITIVE LOGITS
    å¿«æīĭ
    0.11
    ä¼ļéķ¿
    0.10
    åİ¿éķ¿
    0.09
    éĿĴå°ijå¹´
    0.09
     jam
    0.09
     lic
    0.08
    éĺļ
    0.08
    _locals
    0.08
    主å¸Ń
    0.08
    åīįéĿ¢
    0.08
    Activations Density 0.058%

    No Known Activations