© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36717
    Prev
    Next
    INDEX
    Explanations

    field, problem, question, concept, source, case, role

    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
    åĽĽçº§
    -0.09
    æĥħåĨµè¿Ľè¡Į
    -0.08
    ike
    -0.08
    缸åħ³æĶ¿çŃĸ
    -0.08
    Carl
    -0.07
    iated
    -0.07
     Stafford
    -0.07
    ãģĮãĤī
    -0.07
    alis
    -0.07
    ect
    -0.07
    POSITIVE LOGITS
     reason
    0.10
    _bio
    0.10
    è¿ĺåı¯ä»¥
    0.09
    æĪij个人
    0.09
     chance
    0.09
    车åŃIJ
    0.09
     Heck
    0.09
    çī¹çĤ¹æĺ¯
    0.09
    è¿ĺä¸į
    0.09
    ä¹ŁåĽłæѤ
    0.08
    Activations Density 0.326%

    No Known Activations