© 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. 9824
    Prev
    Next
    INDEX
    Explanations

    disclosure of conflicts of interest

    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
    æ²ī
    -0.09
    çĵ¦
    -0.09
    _ROUT
    -0.08
    èĩªçĦ¶çķĮ
    -0.08
    æĪIJçĨŁ
    -0.08
    åij¨ä¸Ģ
    -0.08
     suing
    -0.08
     Fay
    -0.08
    æĺ¥é£İ
    -0.08
    èĹī
    -0.08
    POSITIVE LOGITS
    åĽŀéģ¿
    0.14
     bias
    0.11
    åħ³èģĶ交æĺĵ
    0.10
    Disclosure
    0.10
    bias
    0.10
     disclaimer
    0.09
     independence
    0.09
    éħ¬
    0.09
     Bias
    0.09
    åħįè´£
    0.09
    Activations Density 0.066%

    No Known Activations