© 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. 33878
    Prev
    Next
    INDEX
    Explanations

    settled or stumbled upon

    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
    æݨ
    -0.09
    è¿ŀäºij
    -0.09
    骧
    -0.08
    婵
    -0.08
    ä¼Ĺ人
    -0.08
    follow
    -0.08
     çıkar
    -0.08
    -init
    -0.07
    æŃ£å½ĵ
    -0.07
    chnitt
    -0.07
    POSITIVE LOGITS
    éĢīæĭ©äºĨ
    0.13
    åģľçķĻåľ¨
    0.13
    èIJ½åĪ°
    0.12
    èIJ½åľ¨
    0.12
    åĩĨ
    0.11
    å®ļäºĨ
    0.10
    å®ļå±ħ
    0.10
    èģļçĦ¦
    0.10
    é¦ĸéĢī
    0.10
    éĶļ
    0.10
    Activations Density 0.068%

    No Known Activations