© 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. 53559
    Prev
    Next
    INDEX
    Explanations

    phrase separation, lists, or questions

    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
    çļĦ带é¢Ĩ
    -0.11
    æĥħåĨµè¿Ľè¡Į
    -0.10
    åĪļéľĢ
    -0.10
    æį¢æĿ¥
    -0.09
    ä¹ĭå¤Ħ
    -0.09
    åĵĪå°Ķ
    -0.09
    çIJ®
    -0.09
    è¿Ľè´§
    -0.09
    è½°
    -0.09
    å²Į
    -0.09
    POSITIVE LOGITS
    TypeDef
    0.10
    è¦ģ注æĦı
    0.10
    åĤį
    0.10
    注æĦı
    0.09
    /pm
    0.08
    åįĥä¸ĩåĪ«
    0.08
    /or
    0.08
     маÑĢ
    0.08
    ableObject
    0.08
     Needless
    0.08
    Activations Density 0.033%

    No Known Activations