© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37044
    Prev
    Next
    INDEX
    Explanations

    reality

    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
    åı¤
    -0.10
    çIJ®
    -0.09
    侯
    -0.09
    æĶ¾æĿ¾
    -0.09
    çĻ½çĻ½
    -0.09
    @student
    -0.09
    าà¸ĩ
    -0.08
    棵
    -0.08
    ela
    -0.08
     ker
    -0.08
    POSITIVE LOGITS
     reality
    0.31
    çİ°å®ŀ
    0.27
     Reality
    0.27
     realities
    0.25
    Reality
    0.24
    å®ŀéĻħæĥħåĨµ
    0.22
     réalité
    0.21
     realtÃł
    0.20
     íĺĦìĭ¤
    0.19
    çı¾å¯¦
    0.19
    Activations Density 0.080%

    No Known Activations