© 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. 27010
    Prev
    Next
    INDEX
    Explanations

    teddy, barbie, labrador, chubby, grizzly

    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
    夷
    -0.10
    chor
    -0.09
    æ¯ĶåĪ©
    -0.09
    ãĤ¹ãĥ¼ãĥijãĥ¼
    -0.09
     Toro
    -0.09
    annel
    -0.09
    éĢļè¡Į
    -0.09
    ä½ľåĵģåĨħ容
    -0.08
    nbsp
    -0.08
    èĤ¼
    -0.08
    POSITIVE LOGITS
    ãģ¾ãģ¾
    0.09
    çıij
    0.08
    èĩªè±ª
    0.08
    bear
    0.08
    åģļè¿ĩ
    0.08
    åı£å²¸
    0.08
    èķ¤
    0.08
    å½
    0.08
    fone
    0.08
     Inn
    0.08
    Activations Density 0.002%

    No Known Activations