© 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. 2422
    Prev
    Next
    INDEX
    Explanations

    forbidden fruit

    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
    woke
    -0.08
     Getty
    -0.08
     Pit
    -0.08
    ivet
    -0.08
    è¨Ģ论
    -0.07
    atest
    -0.07
    æĬ¥
    -0.07
    綾
    -0.07
     nave
    -0.07
    伤çĹħ
    -0.07
    POSITIVE LOGITS
    åıįèĢĮ
    0.11
    èĵ¬
    0.10
    vinc
    0.10
    缸åıį
    0.10
    å´¦
    0.10
    ä»ĵ
    0.10
    æĢ»æĶ¶åħ¥
    0.10
    andel
    0.09
    æĸ°çĶŁ
    0.09
    çļĩ家
    0.09
    Activations Density 0.046%

    No Known Activations