© 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. 1759
    Prev
    Next
    INDEX
    Explanations

    state of belief or intention

    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
    æݩ饰
    -0.09
    éĺĻ
    -0.09
    mention
    -0.09
     mention
    -0.08
    ETCH
    -0.08
     Lair
    -0.08
    饥饿
    -0.08
     ÐijолÑĮ
    -0.08
     wah
    -0.08
    Ñĩи
    -0.08
    POSITIVE LOGITS
    认为
    0.12
    å½ĵçĦ¶æĺ¯
    0.12
    æĺ¯è¦ģ
    0.10
    èªįçĤº
    0.10
    è°Ĩ
    0.10
    æĦıåĽ¾
    0.10
    éĢµ
    0.10
    å°±æĺ¯è¦ģ
    0.09
    å¸ĮæľĽéĢļè¿ĩ
    0.09
     intention
    0.09
    Activations Density 0.079%

    No Known Activations