© 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. 34660
    Prev
    Next
    INDEX
    Explanations

    singing voice

    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
    们
    -0.09
    çĪ¶åŃIJ
    -0.08
    åĢij
    -0.08
    åıĮèµ¢
    -0.08
    å°ıå¿ĥ翼翼
    -0.08
     дог
    -0.08
    adge
    -0.08
     Separate
    -0.08
    yle
    -0.08
    cope
    -0.08
    POSITIVE LOGITS
    çĪ±å°Ķåħ°
    0.10
    è´¨
    0.10
    飨
    0.09
    ÑĤÑıж
    0.09
    åķĸ
    0.09
    åįģå¹´
    0.09
    .osgi
    0.09
    éĺ¶
    0.09
    丢äºĨ
    0.09
    è¶ĬæĿ¥è¶Ĭ好
    0.09
    Activations Density 0.036%

    No Known Activations