© 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. 26981
    Prev
    Next
    INDEX
    Explanations

    illusion and delusions

    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
    åĭį
    -0.09
    ossa
    -0.09
    æī¹è¯Ħ
    -0.08
    opor
    -0.08
    責
    -0.08
    çIJħ
    -0.08
    路桥
    -0.08
    Ñįм
    -0.08
    çĥĬ
    -0.08
    潺
    -0.08
    POSITIVE LOGITS
    欺éªĹ
    0.19
    误导
    0.18
    èĻļåģĩ
    0.17
    éªĹ
    0.16
     misleading
    0.15
     false
    0.15
    è°İè¨Ģ
    0.14
     deceptive
    0.14
     illusion
    0.13
    false
    0.13
    Activations Density 0.061%

    No Known Activations