© 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. 19192
    Prev
    Next
    INDEX
    Explanations

    than other

    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
    çħħ
    -0.10
    ugen
    -0.09
    åĻ¼
    -0.09
    çĩİ
    -0.09
    çĦĻ
    -0.09
    .Arg
    -0.09
     اÙĦدÙĬÙĨ
    -0.09
     Hermes
    -0.09
    usted
    -0.09
    Fuse
    -0.08
    POSITIVE LOGITS
    åIJĮç±»
    0.16
    åħ¶ä»ĸ
    0.14
     other
    0.13
    åħ¶ä»ĸçļĦ
    0.13
    åĪ«çļĦ
    0.13
    åħ¶å®ĥ
    0.12
    主æµģ
    0.12
    ä»ĸãģ®
    0.12
    大å¤ļæķ°
    0.11
    æĻ®éĢļ
    0.11
    Activations Density 0.111%

    No Known Activations