© 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. 49554
    Prev
    Next
    INDEX
    Explanations

    X-ray diagnostic radiation

    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
     Cunningham
    -0.11
    éĻįèIJ½
    -0.10
    è¡¡
    -0.10
    ä¸į顾
    -0.10
    éĹŃçݯ
    -0.10
    íĤ¹
    -0.09
    éĹ®éĹ®
    -0.09
    çĽ¯çĿĢ
    -0.09
     окÑĢÑĥ
    -0.09
    éĤł
    -0.09
    POSITIVE LOGITS
    æĶ¾å°Ħ
    0.10
     radio
    0.09
    éŀŃ
    0.08
    ä¸ĬéŨ
    0.08
    2
    0.08
     Practices
    0.08
     practices
    0.08
    7
    0.08
    çħ§çīĩ
    0.08
     shoot
    0.08
    Activations Density 0.206%

    No Known Activations