© 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. 27209
    Prev
    Next
    INDEX
    Explanations

    puppet, doll, dummy, control

    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
     dim
    -0.10
    OOT
    -0.09
    æĭ¦
    -0.09
    ç´¯
    -0.09
    ä¸ĢæĬ¹
    -0.09
    æ¿ł
    -0.09
    qid
    -0.09
    æĭ¦æĪª
    -0.08
    çªĸ
    -0.08
    æ³ħ
    -0.08
    POSITIVE LOGITS
    åĤĢ
    0.14
    æĵįæݧ
    0.13
     puppet
    0.11
    çİ©åħ·
    0.11
    æİĮæݧ
    0.11
    æĵį纵
    0.11
    åĪį
    0.10
    dummy
    0.09
    çĸĻ
    0.09
     doll
    0.09
    Activations Density 0.050%

    No Known Activations