© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7598
    Prev
    Next
    INDEX
    Explanations

    deficiency or deficit

    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
    eller
    -0.11
    åİļåİļ
    -0.09
    åį¿
    -0.09
    Slash
    -0.09
    æĪ´ä¸Ĭ
    -0.09
    ically
    -0.08
    æĭ¬
    -0.08
    iers
    -0.08
    红åĪ©
    -0.08
    åħ³éĶ®æŶåĪ»
    -0.08
    POSITIVE LOGITS
    ä¹ĭå¤Ħ
    0.11
    æĨ¾
    0.10
    åĬ²
    0.09
    缺
    0.09
    æĸĩåĮĸåºķèķ´
    0.09
    缺çĤ¹
    0.09
    IBLE
    0.08
     lineno
    0.08
    åĵģ
    0.08
    累累
    0.08
    Activations Density 0.046%

    No Known Activations