© 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. 56662
    Prev
    Next
    INDEX
    Explanations

    musical artists or groups

    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
    æĬĹåĩ»
    -0.08
    åĪ¹
    -0.08
    Plug
    -0.08
    æĪĬ
    -0.08
    å¹½é»ĺ
    -0.08
    quip
    -0.08
    éĹ¹
    -0.08
     extr
    -0.08
    kus
    -0.07
    (exp
    -0.07
    POSITIVE LOGITS
     Morales
    0.10
    ç°Į
    0.10
    女åıĭ
    0.10
     Äijè
    0.09
    éĺµéĺµ
    0.09
    éĢīæīĭ
    0.09
    ä¿Ŀå¯Ĩ
    0.09
    å¸Ľ
    0.09
     Ore
    0.08
    ç¥ĸ
    0.08
    Activations Density 0.032%

    No Known Activations