© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36358
    Prev
    Next
    INDEX
    Explanations

    LinkedIn professional networking

    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
    缦
    -0.10
    伪
    -0.10
    åħ±éĿĴåĽ¢
    -0.10
    backward
    -0.10
    åıijèĤ²
    -0.09
    UCT
    -0.09
    嶷
    -0.09
    åѦä¼ļäºĨ
    -0.08
    cket
    -0.08
    è´Ńçī©
    -0.08
    POSITIVE LOGITS
    .linkedin
    0.11
     LinkedIn
    0.11
    exec
    0.10
    èģĮä¸ļçĶŁæ¶¯
    0.10
     Exec
    0.09
     Linkedin
    0.09
    LinkedIn
    0.09
    人çĶŁçļĦ
    0.09
    é«ĺ管
    0.08
     lÆ°Æ¡ng
    0.08
    Activations Density 0.147%

    No Known Activations