© 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. 53410
    Prev
    Next
    INDEX
    Explanations

    alternative medicine

    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
    æŀģéĻIJ
    -0.09
    è¸Į
    -0.08
    enge
    -0.08
    anth
    -0.08
    è£ģ
    -0.08
    çĶ¸
    -0.08
    åı
    -0.08
    egas
    -0.08
     mach
    -0.08
    éĢĥ
    -0.08
    POSITIVE LOGITS
    伪
    0.12
    ç§ijåѦ
    0.10
     pseud
    0.10
    诳
    0.10
    pseudo
    0.10
     пÑģ
    0.10
    ä¸įçIJĨ
    0.10
    声称
    0.09
    è¿ĻäºĽä¸ľè¥¿
    0.09
    CLAIM
    0.09
    Activations Density 0.128%

    No Known Activations