© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 698
    Prev
    Next
    INDEX
    Explanations

    TV, cable, content, Bell, Disney

    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
    Negative Logits
    å¾ĢæĿ¥
    -0.12
    åĻ¤
    -0.10
    æĬ¢æķij
    -0.10
    ylon
    -0.09
    طة
    -0.09
    imulator
    -0.09
    æ·±åħ¥å¼Ģå±ķ
    -0.09
    _MACHINE
    -0.09
    alah
    -0.09
    åŁĭ
    -0.09
    POSITIVE LOGITS
    åį«æĺŁ
    0.09
    SV
    0.09
    æĢĿè·¯
    0.08
    æŃ£å½ĵ
    0.08
     SV
    0.08
    оÑĢÑĤ
    0.08
     Blu
    0.08
    çĪ±å¥ĩèīº
    0.08
    éĤ¸
    0.08
    unc
    0.08
    Activations Density 0.307%

    No Known Activations