© 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. 17005
    Prev
    Next
    INDEX
    Explanations

    telnet, television, telstra, telehealth

    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
    ìį¨
    -0.14
    enance
    -0.12
    sWith
    -0.11
     ÑĤомÑĥ
    -0.10
    eur
    -0.10
    ors
    -0.10
     testament
    -0.09
    sc
    -0.09
    erty
    -0.09
    媳
    -0.09
    POSITIVE LOGITS
     ìĿĺíķ´
    0.11
    levision
    0.09
    ight
    0.09
     tun
    0.09
    AndView
    0.09
    SCORE
    0.09
    ists
    0.09
    éĺŁä¼į
    0.09
    ijn
    0.09
    大楼
    0.09
    Activations Density 0.083%

    No Known Activations