© 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. 33959
    Prev
    Next
    INDEX
    Explanations

    comeback and reunion

    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
    çĸ¼
    -0.09
    ways
    -0.09
    çļĦæĥħ绪
    -0.09
    çļĦ帮åĬ©
    -0.09
    çī¹æ®ĬçļĦ
    -0.08
    UMENT
    -0.08
    ãģĹãģ¾ãģĨ
    -0.08
    립
    -0.08
    uka
    -0.08
    ights
    -0.08
    POSITIVE LOGITS
    åĴĮåıijå±ķ
    0.12
    ä¹ĭä½ľ
    0.11
    ä¸İåıijå±ķ
    0.11
    ä¹ĭè·¯
    0.10
    åĬ¨äºº
    0.09
    åĵķ
    0.09
    äºĨä¸Ģæī¹
    0.09
    èĩ³äºİ
    0.09
    ivan
    0.09
    аÑĢа
    0.08
    Activations Density 0.005%

    No Known Activations